< Prev | Home | Model | Random | Next >

Model: GELU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 625 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')



Text #0

Max Range: 6.1244. Min Range: -6.1244

Max Act: 6.1244. Min Act: -0.1700

Data Index: 448362 (C4 (Web Text))

Max Activating Token Index: 683

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 6.1244. Min Range: -6.1244

Max Act: 6.0306. Min Act: -0.1700

Data Index: 976239 (C4 (Web Text))

Max Activating Token Index: 525

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 6.1244. Min Range: -6.1244

Max Act: 5.9056. Min Act: -0.1700

Data Index: 486572 (C4 (Web Text))

Max Activating Token Index: 853

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 6.1244. Min Range: -6.1244

Max Act: 5.9994. Min Act: -0.1700

Data Index: 1311872 (C4 (Web Text))

Max Activating Token Index: 980

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 6.1244. Min Range: -6.1244

Max Act: 5.9994. Min Act: -0.1700

Data Index: 636608 (C4 (Web Text))

Max Activating Token Index: 994

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 6.1244. Min Range: -6.1244

Max Act: 5.9369. Min Act: -0.1700

Data Index: 1520803 (Python Code)

Max Activating Token Index: 947

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 6.1244. Min Range: -6.1244

Max Act: 5.8431. Min Act: -0.1700

Data Index: 229759 (C4 (Web Text))

Max Activating Token Index: 611

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 6.1244. Min Range: -6.1244

Max Act: 5.8744. Min Act: -0.1700

Data Index: 720627 (C4 (Web Text))

Max Activating Token Index: 331

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 6.1244. Min Range: -6.1244

Max Act: 5.8744. Min Act: -0.1700

Data Index: 1339411 (C4 (Web Text))

Max Activating Token Index: 417

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 6.1244. Min Range: -6.1244

Max Act: 5.8431. Min Act: -0.1700

Data Index: 824583 (C4 (Web Text))

Max Activating Token Index: 241

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 6.1244. Min Range: -6.1244

Max Act: 5.8431. Min Act: -0.1700

Data Index: 1077065 (C4 (Web Text))

Max Activating Token Index: 878

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 6.1244. Min Range: -6.1244

Max Act: 5.8119. Min Act: -0.1700

Data Index: 765232 (C4 (Web Text))

Max Activating Token Index: 759

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 6.1244. Min Range: -6.1244

Max Act: 5.8119. Min Act: -0.1700

Data Index: 204441 (C4 (Web Text))

Max Activating Token Index: 512

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 6.1244. Min Range: -6.1244

Max Act: 5.7494. Min Act: -0.1700

Data Index: 1534726 (Python Code)

Max Activating Token Index: 98

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 6.1244. Min Range: -6.1244

Max Act: 5.7181. Min Act: -0.1700

Data Index: 86616 (C4 (Web Text))

Max Activating Token Index: 657

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 6.1244. Min Range: -6.1244

Max Act: 5.8431. Min Act: -0.1700

Data Index: 628063 (C4 (Web Text))

Max Activating Token Index: 534

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 6.1244. Min Range: -6.1244

Max Act: 5.6869. Min Act: -0.1700

Data Index: 203689 (C4 (Web Text))

Max Activating Token Index: 113

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 6.1244. Min Range: -6.1244

Max Act: 5.6869. Min Act: -0.1700

Data Index: 108724 (C4 (Web Text))

Max Activating Token Index: 232

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 6.1244. Min Range: -6.1244

Max Act: 5.8119. Min Act: -0.1700

Data Index: 309329 (C4 (Web Text))

Max Activating Token Index: 767

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 6.1244. Min Range: -6.1244

Max Act: 5.7181. Min Act: -0.1700

Data Index: 638158 (C4 (Web Text))

Max Activating Token Index: 895

Click toggle to see full text

Truncated

Full Text #19