Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6102 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3469. Min Range: -0.3469

Max Act: 0.3469. Min Act: -0.0000

Data Index: 1239478 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 0.3469. Min Range: -0.3469

Max Act: 0.3426. Min Act: -0.0000

Data Index: 304698 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 0.3469. Min Range: -0.3469

Max Act: 0.3212. Min Act: -0.0000

Data Index: 527078 (C4 (Web Text))

Max Activating Token Index: 390

Text #3

Max Range: 0.3469. Min Range: -0.3469

Max Act: 0.3195. Min Act: -0.0000

Data Index: 202328 (C4 (Web Text))

Max Activating Token Index: 848

Text #4

Max Range: 0.3469. Min Range: -0.3469

Max Act: 0.3123. Min Act: -0.0000

Data Index: 957167 (C4 (Web Text))

Max Activating Token Index: 1006

Text #5

Max Range: 0.3469. Min Range: -0.3469

Max Act: 0.2734. Min Act: -0.0000

Data Index: 1054088 (C4 (Web Text))

Max Activating Token Index: 140

Text #6

Max Range: 0.3469. Min Range: -0.3469

Max Act: 0.2618. Min Act: -0.0000

Data Index: 1054876 (C4 (Web Text))

Max Activating Token Index: 596

Text #7

Max Range: 0.3469. Min Range: -0.3469

Max Act: 0.2174. Min Act: -0.0000

Data Index: 237267 (C4 (Web Text))

Max Activating Token Index: 893

Text #8

Max Range: 0.3469. Min Range: -0.3469

Max Act: 0.2239. Min Act: -0.0000

Data Index: 1220664 (C4 (Web Text))

Max Activating Token Index: 799

Text #9

Max Range: 0.3469. Min Range: -0.3469

Max Act: 0.2431. Min Act: -0.0000

Data Index: 678323 (C4 (Web Text))

Max Activating Token Index: 925

Text #10

Max Range: 0.3469. Min Range: -0.3469

Max Act: 0.2374. Min Act: -0.0000

Data Index: 1109463 (C4 (Web Text))

Max Activating Token Index: 234

Text #11

Max Range: 0.3469. Min Range: -0.3469

Max Act: 0.2230. Min Act: -0.0000

Data Index: 793655 (C4 (Web Text))

Max Activating Token Index: 467

Text #12

Max Range: 0.3469. Min Range: -0.3469

Max Act: 0.2138. Min Act: -0.0000

Data Index: 198709 (C4 (Web Text))

Max Activating Token Index: 990

Text #13

Max Range: 0.3469. Min Range: -0.3469

Max Act: 0.2191. Min Act: -0.0000

Data Index: 492716 (C4 (Web Text))

Max Activating Token Index: 749

Text #14

Max Range: 0.3469. Min Range: -0.3469

Max Act: 0.2493. Min Act: -0.0000

Data Index: 318495 (C4 (Web Text))

Max Activating Token Index: 695

Text #15

Max Range: 0.3469. Min Range: -0.3469

Max Act: 0.2348. Min Act: -0.0000

Data Index: 816094 (C4 (Web Text))

Max Activating Token Index: 72

Text #16

Max Range: 0.3469. Min Range: -0.3469

Max Act: 0.1954. Min Act: -0.0000

Data Index: 279030 (C4 (Web Text))

Max Activating Token Index: 898

Text #17

Max Range: 0.3469. Min Range: -0.3469

Max Act: 0.2088. Min Act: -0.0000

Data Index: 910834 (C4 (Web Text))

Max Activating Token Index: 476

Text #18

Max Range: 0.3469. Min Range: -0.3469

Max Act: 0.1995. Min Act: -0.0000

Data Index: 841232 (C4 (Web Text))

Max Activating Token Index: 758

Text #19

Max Range: 0.3469. Min Range: -0.3469

Max Act: 0.2195. Min Act: -0.0000

Data Index: 46962 (C4 (Web Text))

Max Activating Token Index: 997