< Prev | Home | Model | Random | Next >

Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 143 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')



Text #0

Max Range: 3.0291. Min Range: -3.0291

Max Act: 3.0291. Min Act: -0.1700

Data Index: 488950 (C4 (Web Text))

Max Activating Token Index: 858

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.0291. Min Range: -3.0291

Max Act: 3.0133. Min Act: -0.1700

Data Index: 187948 (C4 (Web Text))

Max Activating Token Index: 53

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.0291. Min Range: -3.0291

Max Act: 3.0291. Min Act: -0.1700

Data Index: 927024 (C4 (Web Text))

Max Activating Token Index: 421

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.0291. Min Range: -3.0291

Max Act: 2.9975. Min Act: -0.1700

Data Index: 1032452 (C4 (Web Text))

Max Activating Token Index: 316

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.0291. Min Range: -3.0291

Max Act: 2.9500. Min Act: -0.1700

Data Index: 385693 (C4 (Web Text))

Max Activating Token Index: 190

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.0291. Min Range: -3.0291

Max Act: 2.9817. Min Act: -0.1700

Data Index: 635546 (C4 (Web Text))

Max Activating Token Index: 646

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.0291. Min Range: -3.0291

Max Act: 2.9500. Min Act: -0.1700

Data Index: 899528 (C4 (Web Text))

Max Activating Token Index: 298

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.0291. Min Range: -3.0291

Max Act: 2.9817. Min Act: -0.1700

Data Index: 512220 (C4 (Web Text))

Max Activating Token Index: 54

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.0291. Min Range: -3.0291

Max Act: 2.9342. Min Act: -0.1700

Data Index: 431755 (C4 (Web Text))

Max Activating Token Index: 52

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.0291. Min Range: -3.0291

Max Act: 2.9183. Min Act: -0.1700

Data Index: 646227 (C4 (Web Text))

Max Activating Token Index: 704

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.0291. Min Range: -3.0291

Max Act: 2.9183. Min Act: -0.1700

Data Index: 274556 (C4 (Web Text))

Max Activating Token Index: 898

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.0291. Min Range: -3.0291

Max Act: 2.9659. Min Act: -0.1700

Data Index: 1234027 (C4 (Web Text))

Max Activating Token Index: 863

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.0291. Min Range: -3.0291

Max Act: 2.9342. Min Act: -0.1700

Data Index: 101218 (C4 (Web Text))

Max Activating Token Index: 293

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.0291. Min Range: -3.0291

Max Act: 2.9183. Min Act: -0.1700

Data Index: 742501 (C4 (Web Text))

Max Activating Token Index: 33

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.0291. Min Range: -3.0291

Max Act: 2.9500. Min Act: -0.1700

Data Index: 940774 (C4 (Web Text))

Max Activating Token Index: 76

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.0291. Min Range: -3.0291

Max Act: 2.9183. Min Act: -0.1700

Data Index: 325855 (C4 (Web Text))

Max Activating Token Index: 907

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.0291. Min Range: -3.0291

Max Act: 2.9183. Min Act: -0.1700

Data Index: 1378518 (Python Code)

Max Activating Token Index: 136

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.0291. Min Range: -3.0291

Max Act: 2.9183. Min Act: -0.1700

Data Index: 1381289 (Python Code)

Max Activating Token Index: 55

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.0291. Min Range: -3.0291

Max Act: 2.8708. Min Act: -0.1700

Data Index: 1656068 (Python Code)

Max Activating Token Index: 226

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.0291. Min Range: -3.0291

Max Act: 2.9183. Min Act: -0.1700

Data Index: 349840 (C4 (Web Text))

Max Activating Token Index: 301

Click toggle to see full text

Truncated

Full Text #19