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

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

Neuron 3734 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9460. Min Range: -0.9460

Max Act: 0.9460. Min Act: -0.0000

Data Index: 401915 (C4 (Web Text))

Max Activating Token Index: 792

Text #1

Max Range: 0.9460. Min Range: -0.9460

Max Act: 0.3877. Min Act: -0.0000

Data Index: 936334 (C4 (Web Text))

Max Activating Token Index: 474

Text #2

Max Range: 0.9460. Min Range: -0.9460

Max Act: 0.3698. Min Act: -0.0001

Data Index: 567406 (C4 (Web Text))

Max Activating Token Index: 579

Text #3

Max Range: 0.9460. Min Range: -0.9460

Max Act: 0.3618. Min Act: -0.0001

Data Index: 855354 (C4 (Web Text))

Max Activating Token Index: 95

Text #4

Max Range: 0.9460. Min Range: -0.9460

Max Act: 0.3647. Min Act: -0.0000

Data Index: 1114278 (C4 (Web Text))

Max Activating Token Index: 405

Text #5

Max Range: 0.9460. Min Range: -0.9460

Max Act: 0.3401. Min Act: -0.0000

Data Index: 209776 (C4 (Web Text))

Max Activating Token Index: 124

Text #6

Max Range: 0.9460. Min Range: -0.9460

Max Act: 0.3701. Min Act: -0.0000

Data Index: 1182491 (C4 (Web Text))

Max Activating Token Index: 766

Text #7

Max Range: 0.9460. Min Range: -0.9460

Max Act: 0.3483. Min Act: -0.0000

Data Index: 476068 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 0.9460. Min Range: -0.9460

Max Act: 0.3269. Min Act: -0.0001

Data Index: 771475 (C4 (Web Text))

Max Activating Token Index: 625

Text #9

Max Range: 0.9460. Min Range: -0.9460

Max Act: 0.3206. Min Act: -0.0000

Data Index: 1315094 (C4 (Web Text))

Max Activating Token Index: 338

Text #10

Max Range: 0.9460. Min Range: -0.9460

Max Act: 0.3233. Min Act: -0.0000

Data Index: 1082015 (C4 (Web Text))

Max Activating Token Index: 399

Text #11

Max Range: 0.9460. Min Range: -0.9460

Max Act: 0.3049. Min Act: -0.0000

Data Index: 315811 (C4 (Web Text))

Max Activating Token Index: 305

Text #12

Max Range: 0.9460. Min Range: -0.9460

Max Act: 0.2894. Min Act: -0.0000

Data Index: 1136530 (C4 (Web Text))

Max Activating Token Index: 946

Text #13

Max Range: 0.9460. Min Range: -0.9460

Max Act: 0.3107. Min Act: -0.0000

Data Index: 739325 (C4 (Web Text))

Max Activating Token Index: 871

Text #14

Max Range: 0.9460. Min Range: -0.9460

Max Act: 0.2995. Min Act: -0.0000

Data Index: 283057 (C4 (Web Text))

Max Activating Token Index: 694

Text #15

Max Range: 0.9460. Min Range: -0.9460

Max Act: 0.3097. Min Act: -0.0000

Data Index: 1258271 (C4 (Web Text))

Max Activating Token Index: 641

Text #16

Max Range: 0.9460. Min Range: -0.9460

Max Act: 0.3238. Min Act: -0.0000

Data Index: 87860 (C4 (Web Text))

Max Activating Token Index: 939

Text #17

Max Range: 0.9460. Min Range: -0.9460

Max Act: 0.2788. Min Act: -0.0000

Data Index: 1306068 (C4 (Web Text))

Max Activating Token Index: 230

Text #18

Max Range: 0.9460. Min Range: -0.9460

Max Act: 0.2751. Min Act: -0.0000

Data Index: 1295916 (C4 (Web Text))

Max Activating Token Index: 370

Text #19

Max Range: 0.9460. Min Range: -0.9460

Max Act: 0.3042. Min Act: -0.0000

Data Index: 1129957 (C4 (Web Text))

Max Activating Token Index: 982