Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3323 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.4932. Min Act: -0.0000

Data Index: 986465 (C4 (Web Text))

Max Activating Token Index: 973

Text #1

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.4594. Min Act: -0.0000

Data Index: 1233821 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.4188. Min Act: -0.0000

Data Index: 158447 (C4 (Web Text))

Max Activating Token Index: 714

Text #3

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.4180. Min Act: -0.0001

Data Index: 60615 (C4 (Web Text))

Max Activating Token Index: 724

Text #4

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.4202. Min Act: -0.0001

Data Index: 378036 (C4 (Web Text))

Max Activating Token Index: 676

Text #5

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.3849. Min Act: -0.0000

Data Index: 1058374 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.3737. Min Act: -0.0000

Data Index: 984393 (C4 (Web Text))

Max Activating Token Index: 266

Text #7

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.3994. Min Act: -0.0000

Data Index: 880857 (C4 (Web Text))

Max Activating Token Index: 764

Text #8

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.3622. Min Act: -0.0000

Data Index: 290865 (C4 (Web Text))

Max Activating Token Index: 501

Text #9

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.3570. Min Act: -0.0000

Data Index: 656671 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.3411. Min Act: -0.0000

Data Index: 821067 (C4 (Web Text))

Max Activating Token Index: 165

Text #11

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.3379. Min Act: -0.0000

Data Index: 96436 (C4 (Web Text))

Max Activating Token Index: 188

Text #12

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.3366. Min Act: -0.0000

Data Index: 764256 (C4 (Web Text))

Max Activating Token Index: 626

Text #13

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.3460. Min Act: -0.0000

Data Index: 1109426 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.3321. Min Act: -0.0000

Data Index: 42500 (C4 (Web Text))

Max Activating Token Index: 186

Text #15

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.3202. Min Act: -0.0000

Data Index: 153109 (C4 (Web Text))

Max Activating Token Index: 327

Text #16

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.3402. Min Act: -0.0000

Data Index: 1191536 (C4 (Web Text))

Max Activating Token Index: 328

Text #17

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.3243. Min Act: 0.0000

Data Index: 689914 (C4 (Web Text))

Max Activating Token Index: 652

Text #18

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.3228. Min Act: -0.0000

Data Index: 697387 (C4 (Web Text))

Max Activating Token Index: 585

Text #19

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.3228. Min Act: -0.0000

Data Index: 834888 (C4 (Web Text))

Max Activating Token Index: 413