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

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

Neuron 5855 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: 1.7089. Min Range: -1.7089

Max Act: 1.7089. Min Act: -0.0000

Data Index: 679344 (C4 (Web Text))

Max Activating Token Index: 372

Text #1

Max Range: 1.7089. Min Range: -1.7089

Max Act: 1.6417. Min Act: -0.0000

Data Index: 878499 (C4 (Web Text))

Max Activating Token Index: 639

Text #2

Max Range: 1.7089. Min Range: -1.7089

Max Act: 1.5151. Min Act: -0.0000

Data Index: 434916 (C4 (Web Text))

Max Activating Token Index: 211

Text #3

Max Range: 1.7089. Min Range: -1.7089

Max Act: 1.4797. Min Act: -0.0000

Data Index: 676888 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 1.7089. Min Range: -1.7089

Max Act: 1.5549. Min Act: -0.0000

Data Index: 1325108 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 1.7089. Min Range: -1.7089

Max Act: 1.4527. Min Act: -0.0000

Data Index: 1005392 (C4 (Web Text))

Max Activating Token Index: 506

Text #6

Max Range: 1.7089. Min Range: -1.7089

Max Act: 1.4908. Min Act: -0.0000

Data Index: 347965 (C4 (Web Text))

Max Activating Token Index: 486

Text #7

Max Range: 1.7089. Min Range: -1.7089

Max Act: 1.5194. Min Act: -0.0000

Data Index: 560614 (C4 (Web Text))

Max Activating Token Index: 874

Text #8

Max Range: 1.7089. Min Range: -1.7089

Max Act: 1.5240. Min Act: -0.0000

Data Index: 565466 (C4 (Web Text))

Max Activating Token Index: 127

Text #9

Max Range: 1.7089. Min Range: -1.7089

Max Act: 1.4177. Min Act: -0.0000

Data Index: 407585 (C4 (Web Text))

Max Activating Token Index: 944

Text #10

Max Range: 1.7089. Min Range: -1.7089

Max Act: 1.4527. Min Act: -0.0000

Data Index: 430853 (C4 (Web Text))

Max Activating Token Index: 477

Text #11

Max Range: 1.7089. Min Range: -1.7089

Max Act: 1.4134. Min Act: -0.0000

Data Index: 679810 (C4 (Web Text))

Max Activating Token Index: 319

Text #12

Max Range: 1.7089. Min Range: -1.7089

Max Act: 1.4390. Min Act: -0.0000

Data Index: 1298751 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 1.7089. Min Range: -1.7089

Max Act: 1.4355. Min Act: -0.0000

Data Index: 1355393 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 1.7089. Min Range: -1.7089

Max Act: 1.4231. Min Act: -0.0000

Data Index: 841407 (C4 (Web Text))

Max Activating Token Index: 690

Text #15

Max Range: 1.7089. Min Range: -1.7089

Max Act: 1.3523. Min Act: -0.0000

Data Index: 292018 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 1.7089. Min Range: -1.7089

Max Act: 1.3449. Min Act: -0.0000

Data Index: 20789 (C4 (Web Text))

Max Activating Token Index: 693

Text #17

Max Range: 1.7089. Min Range: -1.7089

Max Act: 1.3874. Min Act: -0.0000

Data Index: 909662 (C4 (Web Text))

Max Activating Token Index: 983

Text #18

Max Range: 1.7089. Min Range: -1.7089

Max Act: 1.3355. Min Act: -0.0000

Data Index: 343687 (C4 (Web Text))

Max Activating Token Index: 889

Text #19

Max Range: 1.7089. Min Range: -1.7089

Max Act: 1.4138. Min Act: -0.0000

Data Index: 1299398 (C4 (Web Text))

Max Activating Token Index: 444