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

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

Neuron 2381 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0754. Min Act: -0.0002

Data Index: 1177706 (C4 (Web Text))

Max Activating Token Index: 336

Text #1

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0626. Min Act: -0.0002

Data Index: 225041 (C4 (Web Text))

Max Activating Token Index: 786

Text #2

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0597. Min Act: -0.0002

Data Index: 213862 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0580. Min Act: -0.0002

Data Index: 903910 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0558. Min Act: -0.0002

Data Index: 810166 (C4 (Web Text))

Max Activating Token Index: 248

Text #5

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0543. Min Act: -0.0002

Data Index: 1250476 (C4 (Web Text))

Max Activating Token Index: 490

Text #6

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0523. Min Act: -0.0002

Data Index: 325226 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0518. Min Act: -0.0002

Data Index: 1117955 (C4 (Web Text))

Max Activating Token Index: 643

Text #8

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0503. Min Act: -0.0002

Data Index: 37380 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0494. Min Act: -0.0002

Data Index: 718249 (C4 (Web Text))

Max Activating Token Index: 183

Text #10

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0494. Min Act: -0.0002

Data Index: 416465 (C4 (Web Text))

Max Activating Token Index: 169

Text #11

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0483. Min Act: -0.0002

Data Index: 910117 (C4 (Web Text))

Max Activating Token Index: 620

Text #12

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0472. Min Act: -0.0002

Data Index: 1327579 (C4 (Web Text))

Max Activating Token Index: 572

Text #13

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0475. Min Act: -0.0002

Data Index: 977841 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0469. Min Act: -0.0002

Data Index: 1103529 (C4 (Web Text))

Max Activating Token Index: 380

Text #15

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0473. Min Act: -0.0002

Data Index: 301727 (C4 (Web Text))

Max Activating Token Index: 795

Text #16

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0446. Min Act: -0.0002

Data Index: 1189653 (C4 (Web Text))

Max Activating Token Index: 299

Text #17

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0471. Min Act: -0.0002

Data Index: 250611 (C4 (Web Text))

Max Activating Token Index: 344

Text #18

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0457. Min Act: -0.0002

Data Index: 1129690 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0440. Min Act: -0.0002

Data Index: 309090 (C4 (Web Text))

Max Activating Token Index: 711