Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 633 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5285. Min Range: -0.5285

Max Act: 0.5285. Min Act: -0.0000

Data Index: 38935 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 0.5285. Min Range: -0.5285

Max Act: 0.4331. Min Act: -0.0000

Data Index: 147831 (C4 (Web Text))

Max Activating Token Index: 351

Text #2

Max Range: 0.5285. Min Range: -0.5285

Max Act: 0.4045. Min Act: -0.0000

Data Index: 587370 (C4 (Web Text))

Max Activating Token Index: 341

Text #3

Max Range: 0.5285. Min Range: -0.5285

Max Act: 0.4033. Min Act: -0.0000

Data Index: 1273126 (C4 (Web Text))

Max Activating Token Index: 866

Text #4

Max Range: 0.5285. Min Range: -0.5285

Max Act: 0.3762. Min Act: -0.0000

Data Index: 156594 (C4 (Web Text))

Max Activating Token Index: 688

Text #5

Max Range: 0.5285. Min Range: -0.5285

Max Act: 0.3759. Min Act: -0.0000

Data Index: 1034616 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 0.5285. Min Range: -0.5285

Max Act: 0.3660. Min Act: -0.0000

Data Index: 313463 (C4 (Web Text))

Max Activating Token Index: 938

Text #7

Max Range: 0.5285. Min Range: -0.5285

Max Act: 0.3600. Min Act: -0.0000

Data Index: 412097 (C4 (Web Text))

Max Activating Token Index: 437

Text #8

Max Range: 0.5285. Min Range: -0.5285

Max Act: 0.3580. Min Act: -0.0000

Data Index: 200780 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 0.5285. Min Range: -0.5285

Max Act: 0.3437. Min Act: -0.0000

Data Index: 713399 (C4 (Web Text))

Max Activating Token Index: 652

Text #10

Max Range: 0.5285. Min Range: -0.5285

Max Act: 0.3590. Min Act: -0.0000

Data Index: 219389 (C4 (Web Text))

Max Activating Token Index: 271

Text #11

Max Range: 0.5285. Min Range: -0.5285

Max Act: 0.3289. Min Act: -0.0000

Data Index: 800271 (C4 (Web Text))

Max Activating Token Index: 240

Text #12

Max Range: 0.5285. Min Range: -0.5285

Max Act: 0.3512. Min Act: -0.0000

Data Index: 1123768 (C4 (Web Text))

Max Activating Token Index: 440

Text #13

Max Range: 0.5285. Min Range: -0.5285

Max Act: 0.3331. Min Act: -0.0000

Data Index: 342826 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 0.5285. Min Range: -0.5285

Max Act: 0.3422. Min Act: -0.0000

Data Index: 800852 (C4 (Web Text))

Max Activating Token Index: 361

Text #15

Max Range: 0.5285. Min Range: -0.5285

Max Act: 0.3206. Min Act: -0.0000

Data Index: 103020 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 0.5285. Min Range: -0.5285

Max Act: 0.3164. Min Act: -0.0000

Data Index: 665035 (C4 (Web Text))

Max Activating Token Index: 105

Text #17

Max Range: 0.5285. Min Range: -0.5285

Max Act: 0.2892. Min Act: -0.0000

Data Index: 1298242 (C4 (Web Text))

Max Activating Token Index: 233

Text #18

Max Range: 0.5285. Min Range: -0.5285

Max Act: 0.2866. Min Act: -0.0000

Data Index: 404599 (C4 (Web Text))

Max Activating Token Index: 684

Text #19

Max Range: 0.5285. Min Range: -0.5285

Max Act: 0.2963. Min Act: -0.0000

Data Index: 123122 (C4 (Web Text))

Max Activating Token Index: 145