< Prev | Home | Model | Random | Next >

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

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

Neuron 96 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 4.8196. Min Range: -4.8196

Max Act: 4.8196. Min Act: -0.1700

Data Index: 6006 (C4 (Web Text))

Max Activating Token Index: 650

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.8196. Min Range: -4.8196

Max Act: 4.6321. Min Act: -0.1700

Data Index: 1220898 (C4 (Web Text))

Max Activating Token Index: 858

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.8196. Min Range: -4.8196

Max Act: 4.6477. Min Act: -0.1700

Data Index: 176156 (C4 (Web Text))

Max Activating Token Index: 897

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.8196. Min Range: -4.8196

Max Act: 4.6164. Min Act: -0.1700

Data Index: 989266 (C4 (Web Text))

Max Activating Token Index: 760

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.8196. Min Range: -4.8196

Max Act: 4.5539. Min Act: -0.1700

Data Index: 1480037 (Python Code)

Max Activating Token Index: 548

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.8196. Min Range: -4.8196

Max Act: 4.4914. Min Act: -0.1700

Data Index: 321652 (C4 (Web Text))

Max Activating Token Index: 12

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.8196. Min Range: -4.8196

Max Act: 4.4602. Min Act: -0.1700

Data Index: 896701 (C4 (Web Text))

Max Activating Token Index: 741

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.8196. Min Range: -4.8196

Max Act: 4.4602. Min Act: -0.1700

Data Index: 516098 (C4 (Web Text))

Max Activating Token Index: 89

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.8196. Min Range: -4.8196

Max Act: 4.4446. Min Act: -0.1700

Data Index: 631898 (C4 (Web Text))

Max Activating Token Index: 651

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.8196. Min Range: -4.8196

Max Act: 4.3977. Min Act: -0.1700

Data Index: 583973 (C4 (Web Text))

Max Activating Token Index: 495

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.8196. Min Range: -4.8196

Max Act: 4.4133. Min Act: -0.1700

Data Index: 76965 (C4 (Web Text))

Max Activating Token Index: 632

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.8196. Min Range: -4.8196

Max Act: 4.4289. Min Act: -0.1700

Data Index: 91905 (C4 (Web Text))

Max Activating Token Index: 496

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.8196. Min Range: -4.8196

Max Act: 4.4133. Min Act: -0.1700

Data Index: 640025 (C4 (Web Text))

Max Activating Token Index: 728

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.8196. Min Range: -4.8196

Max Act: 4.3664. Min Act: -0.1700

Data Index: 1329931 (C4 (Web Text))

Max Activating Token Index: 264

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.8196. Min Range: -4.8196

Max Act: 4.3821. Min Act: -0.1700

Data Index: 1618753 (Python Code)

Max Activating Token Index: 405

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.8196. Min Range: -4.8196

Max Act: 4.3977. Min Act: -0.1700

Data Index: 262128 (C4 (Web Text))

Max Activating Token Index: 9

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.8196. Min Range: -4.8196

Max Act: 4.3508. Min Act: -0.1700

Data Index: 500744 (C4 (Web Text))

Max Activating Token Index: 548

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.8196. Min Range: -4.8196

Max Act: 4.3195. Min Act: -0.1700

Data Index: 575739 (C4 (Web Text))

Max Activating Token Index: 70

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.8196. Min Range: -4.8196

Max Act: 4.3195. Min Act: -0.1700

Data Index: 305466 (C4 (Web Text))

Max Activating Token Index: 824

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.8196. Min Range: -4.8196

Max Act: 4.3195. Min Act: -0.1700

Data Index: 1523146 (Python Code)

Max Activating Token Index: 437

Click toggle to see full text

Truncated

Full Text #19