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

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

Neuron 6129 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.5314. Min Act: -0.0000

Data Index: 114043 (C4 (Web Text))

Max Activating Token Index: 226

Text #1

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.4820. Min Act: -0.0000

Data Index: 666075 (C4 (Web Text))

Max Activating Token Index: 453

Text #2

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.4717. Min Act: -0.0000

Data Index: 738715 (C4 (Web Text))

Max Activating Token Index: 101

Text #3

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.3981. Min Act: -0.0000

Data Index: 504194 (C4 (Web Text))

Max Activating Token Index: 837

Text #4

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.3321. Min Act: -0.0000

Data Index: 418687 (C4 (Web Text))

Max Activating Token Index: 279

Text #5

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.3253. Min Act: -0.0000

Data Index: 863273 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.3086. Min Act: -0.0000

Data Index: 230058 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.3129. Min Act: -0.0000

Data Index: 1246460 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.3205. Min Act: -0.0000

Data Index: 190667 (C4 (Web Text))

Max Activating Token Index: 537

Text #9

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.3361. Min Act: -0.0000

Data Index: 303240 (C4 (Web Text))

Max Activating Token Index: 259

Text #10

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.2778. Min Act: -0.0000

Data Index: 1038723 (C4 (Web Text))

Max Activating Token Index: 961

Text #11

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.2921. Min Act: -0.0000

Data Index: 173276 (C4 (Web Text))

Max Activating Token Index: 501

Text #12

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.2963. Min Act: -0.0000

Data Index: 818356 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.2919. Min Act: -0.0000

Data Index: 14939 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.2616. Min Act: -0.0000

Data Index: 757091 (C4 (Web Text))

Max Activating Token Index: 199

Text #15

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.2739. Min Act: -0.0000

Data Index: 1299199 (C4 (Web Text))

Max Activating Token Index: 525

Text #16

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.2572. Min Act: -0.0000

Data Index: 1208401 (C4 (Web Text))

Max Activating Token Index: 743

Text #17

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.2706. Min Act: -0.0000

Data Index: 639373 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.2549. Min Act: -0.0000

Data Index: 817786 (C4 (Web Text))

Max Activating Token Index: 517

Text #19

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.2462. Min Act: -0.0000

Data Index: 442094 (C4 (Web Text))

Max Activating Token Index: 951