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

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

Neuron 3197 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9134. Min Range: -0.9134

Max Act: 0.8440. Min Act: -0.0000

Data Index: 687072 (C4 (Web Text))

Max Activating Token Index: 192

Text #1

Max Range: 0.9134. Min Range: -0.9134

Max Act: 0.8467. Min Act: -0.0000

Data Index: 765394 (C4 (Web Text))

Max Activating Token Index: 344

Text #2

Max Range: 0.9134. Min Range: -0.9134

Max Act: 0.8260. Min Act: -0.0000

Data Index: 847759 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 0.9134. Min Range: -0.9134

Max Act: 0.9134. Min Act: -0.0000

Data Index: 151190 (C4 (Web Text))

Max Activating Token Index: 427

Text #4

Max Range: 0.9134. Min Range: -0.9134

Max Act: 0.8078. Min Act: -0.0000

Data Index: 1077305 (C4 (Web Text))

Max Activating Token Index: 242

Text #5

Max Range: 0.9134. Min Range: -0.9134

Max Act: 0.7620. Min Act: -0.0000

Data Index: 1076982 (C4 (Web Text))

Max Activating Token Index: 751

Text #6

Max Range: 0.9134. Min Range: -0.9134

Max Act: 0.6899. Min Act: -0.0000

Data Index: 78389 (C4 (Web Text))

Max Activating Token Index: 654

Text #7

Max Range: 0.9134. Min Range: -0.9134

Max Act: 0.7712. Min Act: -0.0000

Data Index: 651904 (C4 (Web Text))

Max Activating Token Index: 991

Text #8

Max Range: 0.9134. Min Range: -0.9134

Max Act: 0.7413. Min Act: -0.0000

Data Index: 314702 (C4 (Web Text))

Max Activating Token Index: 642

Text #9

Max Range: 0.9134. Min Range: -0.9134

Max Act: 0.7524. Min Act: -0.0000

Data Index: 690007 (C4 (Web Text))

Max Activating Token Index: 89

Text #10

Max Range: 0.9134. Min Range: -0.9134

Max Act: 0.7224. Min Act: -0.0000

Data Index: 116132 (C4 (Web Text))

Max Activating Token Index: 981

Text #11

Max Range: 0.9134. Min Range: -0.9134

Max Act: 0.6836. Min Act: -0.0000

Data Index: 668517 (C4 (Web Text))

Max Activating Token Index: 735

Text #12

Max Range: 0.9134. Min Range: -0.9134

Max Act: 0.7290. Min Act: -0.0000

Data Index: 720014 (C4 (Web Text))

Max Activating Token Index: 804

Text #13

Max Range: 0.9134. Min Range: -0.9134

Max Act: 0.7652. Min Act: -0.0000

Data Index: 11027 (C4 (Web Text))

Max Activating Token Index: 528

Text #14

Max Range: 0.9134. Min Range: -0.9134

Max Act: 0.7188. Min Act: -0.0000

Data Index: 247896 (C4 (Web Text))

Max Activating Token Index: 626

Text #15

Max Range: 0.9134. Min Range: -0.9134

Max Act: 0.7151. Min Act: -0.0000

Data Index: 265730 (C4 (Web Text))

Max Activating Token Index: 1003

Text #16

Max Range: 0.9134. Min Range: -0.9134

Max Act: 0.7178. Min Act: -0.0000

Data Index: 1264384 (C4 (Web Text))

Max Activating Token Index: 823

Text #17

Max Range: 0.9134. Min Range: -0.9134

Max Act: 0.6271. Min Act: -0.0000

Data Index: 59802 (C4 (Web Text))

Max Activating Token Index: 905

Text #18

Max Range: 0.9134. Min Range: -0.9134

Max Act: 0.7044. Min Act: -0.0000

Data Index: 1289969 (C4 (Web Text))

Max Activating Token Index: 1015

Text #19

Max Range: 0.9134. Min Range: -0.9134

Max Act: 0.6933. Min Act: -0.0000

Data Index: 1236577 (C4 (Web Text))

Max Activating Token Index: 643