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

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

Neuron 2925 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.6601. Min Act: -0.0001

Data Index: 1322083 (C4 (Web Text))

Max Activating Token Index: 429

Text #1

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.6572. Min Act: -0.0001

Data Index: 939473 (C4 (Web Text))

Max Activating Token Index: 289

Text #2

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.6051. Min Act: -0.0001

Data Index: 857706 (C4 (Web Text))

Max Activating Token Index: 150

Text #3

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.6170. Min Act: -0.0001

Data Index: 461815 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.6045. Min Act: -0.0001

Data Index: 118561 (C4 (Web Text))

Max Activating Token Index: 723

Text #5

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.6216. Min Act: -0.0001

Data Index: 299919 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.5795. Min Act: -0.0001

Data Index: 339013 (C4 (Web Text))

Max Activating Token Index: 694

Text #7

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.6014. Min Act: -0.0001

Data Index: 427655 (C4 (Web Text))

Max Activating Token Index: 765

Text #8

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.5932. Min Act: -0.0001

Data Index: 1052779 (C4 (Web Text))

Max Activating Token Index: 257

Text #9

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.5842. Min Act: -0.0001

Data Index: 1173676 (C4 (Web Text))

Max Activating Token Index: 172

Text #10

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.5839. Min Act: -0.0001

Data Index: 319675 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.6018. Min Act: -0.0001

Data Index: 8751 (C4 (Web Text))

Max Activating Token Index: 720

Text #12

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.5805. Min Act: -0.0001

Data Index: 828572 (C4 (Web Text))

Max Activating Token Index: 428

Text #13

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.5559. Min Act: -0.0001

Data Index: 955425 (C4 (Web Text))

Max Activating Token Index: 949

Text #14

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.5736. Min Act: -0.0001

Data Index: 319031 (C4 (Web Text))

Max Activating Token Index: 470

Text #15

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.5729. Min Act: -0.0001

Data Index: 1114028 (C4 (Web Text))

Max Activating Token Index: 939

Text #16

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.5940. Min Act: -0.0001

Data Index: 195814 (C4 (Web Text))

Max Activating Token Index: 376

Text #17

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.5678. Min Act: -0.0000

Data Index: 769639 (C4 (Web Text))

Max Activating Token Index: 882

Text #18

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.5685. Min Act: -0.0001

Data Index: 1325820 (C4 (Web Text))

Max Activating Token Index: 231

Text #19

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.5821. Min Act: -0.0001

Data Index: 1074316 (C4 (Web Text))

Max Activating Token Index: 887