Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3075 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 8.1182. Min Range: -8.1182

Max Act: 8.1182. Min Act: -0.0000

Data Index: 1502779 (The Pile)

Max Activating Token Index: 92

Text #1

Max Range: 8.1182. Min Range: -8.1182

Max Act: 6.4069. Min Act: -0.0000

Data Index: 695790 (The Pile)

Max Activating Token Index: 261

Text #2

Max Range: 8.1182. Min Range: -8.1182

Max Act: 6.3757. Min Act: -0.0000

Data Index: 1062858 (The Pile)

Max Activating Token Index: 43

Text #3

Max Range: 8.1182. Min Range: -8.1182

Max Act: 6.0901. Min Act: -0.0000

Data Index: 539406 (The Pile)

Max Activating Token Index: 815

Text #4

Max Range: 8.1182. Min Range: -8.1182

Max Act: 6.1334. Min Act: -0.0000

Data Index: 1929499 (The Pile)

Max Activating Token Index: 251

Text #5

Max Range: 8.1182. Min Range: -8.1182

Max Act: 6.1061. Min Act: -0.0000

Data Index: 109736 (The Pile)

Max Activating Token Index: 211

Text #6

Max Range: 8.1182. Min Range: -8.1182

Max Act: 6.0982. Min Act: -0.0000

Data Index: 735887 (The Pile)

Max Activating Token Index: 357

Text #7

Max Range: 8.1182. Min Range: -8.1182

Max Act: 5.8587. Min Act: -0.0000

Data Index: 568581 (The Pile)

Max Activating Token Index: 142

Text #8

Max Range: 8.1182. Min Range: -8.1182

Max Act: 5.9719. Min Act: -0.0000

Data Index: 1654027 (The Pile)

Max Activating Token Index: 538

Text #9

Max Range: 8.1182. Min Range: -8.1182

Max Act: 5.9173. Min Act: -0.0000

Data Index: 114208 (The Pile)

Max Activating Token Index: 582

Text #10

Max Range: 8.1182. Min Range: -8.1182

Max Act: 5.8912. Min Act: -0.0000

Data Index: 1504190 (The Pile)

Max Activating Token Index: 522

Text #11

Max Range: 8.1182. Min Range: -8.1182

Max Act: 6.0440. Min Act: -0.0000

Data Index: 1382978 (The Pile)

Max Activating Token Index: 78

Text #12

Max Range: 8.1182. Min Range: -8.1182

Max Act: 5.9800. Min Act: -0.0000

Data Index: 1000520 (The Pile)

Max Activating Token Index: 975

Text #13

Max Range: 8.1182. Min Range: -8.1182

Max Act: 5.7979. Min Act: -0.0000

Data Index: 1707949 (The Pile)

Max Activating Token Index: 902

Text #14

Max Range: 8.1182. Min Range: -8.1182

Max Act: 5.7762. Min Act: -0.0000

Data Index: 638832 (The Pile)

Max Activating Token Index: 323

Text #15

Max Range: 8.1182. Min Range: -8.1182

Max Act: 5.7386. Min Act: -0.0000

Data Index: 220902 (The Pile)

Max Activating Token Index: 324

Text #16

Max Range: 8.1182. Min Range: -8.1182

Max Act: 5.6926. Min Act: -0.0000

Data Index: 1886408 (The Pile)

Max Activating Token Index: 524

Text #17

Max Range: 8.1182. Min Range: -8.1182

Max Act: 5.6018. Min Act: -0.0000

Data Index: 479182 (The Pile)

Max Activating Token Index: 976

Text #18

Max Range: 8.1182. Min Range: -8.1182

Max Act: 5.6322. Min Act: -0.0000

Data Index: 1725698 (The Pile)

Max Activating Token Index: 906

Text #19

Max Range: 8.1182. Min Range: -8.1182

Max Act: 5.6147. Min Act: -0.0000

Data Index: 412763 (The Pile)

Max Activating Token Index: 663