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

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

Neuron 4419 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8007. Min Range: -1.8007

Max Act: 1.8007. Min Act: -0.0000

Data Index: 1019916 (C4 (Web Text))

Max Activating Token Index: 955

Text #1

Max Range: 1.8007. Min Range: -1.8007

Max Act: 1.6580. Min Act: -0.0000

Data Index: 353438 (C4 (Web Text))

Max Activating Token Index: 190

Text #2

Max Range: 1.8007. Min Range: -1.8007

Max Act: 1.5188. Min Act: 0.0000

Data Index: 461120 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 1.8007. Min Range: -1.8007

Max Act: 1.3274. Min Act: -0.0000

Data Index: 457871 (C4 (Web Text))

Max Activating Token Index: 291

Text #4

Max Range: 1.8007. Min Range: -1.8007

Max Act: 1.1125. Min Act: -0.0000

Data Index: 1265914 (C4 (Web Text))

Max Activating Token Index: 1017

Text #5

Max Range: 1.8007. Min Range: -1.8007

Max Act: 1.1726. Min Act: -0.0000

Data Index: 295811 (C4 (Web Text))

Max Activating Token Index: 846

Text #6

Max Range: 1.8007. Min Range: -1.8007

Max Act: 1.1402. Min Act: -0.0000

Data Index: 394607 (C4 (Web Text))

Max Activating Token Index: 294

Text #7

Max Range: 1.8007. Min Range: -1.8007

Max Act: 1.0657. Min Act: -0.0000

Data Index: 1194932 (C4 (Web Text))

Max Activating Token Index: 577

Text #8

Max Range: 1.8007. Min Range: -1.8007

Max Act: 0.9888. Min Act: -0.0000

Data Index: 97629 (C4 (Web Text))

Max Activating Token Index: 223

Text #9

Max Range: 1.8007. Min Range: -1.8007

Max Act: 0.9744. Min Act: -0.0000

Data Index: 57207 (C4 (Web Text))

Max Activating Token Index: 616

Text #10

Max Range: 1.8007. Min Range: -1.8007

Max Act: 0.9433. Min Act: -0.0000

Data Index: 1357711 (C4 (Web Text))

Max Activating Token Index: 110

Text #11

Max Range: 1.8007. Min Range: -1.8007

Max Act: 0.8836. Min Act: -0.0000

Data Index: 710429 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 1.8007. Min Range: -1.8007

Max Act: 0.9671. Min Act: -0.0000

Data Index: 890584 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 1.8007. Min Range: -1.8007

Max Act: 0.9134. Min Act: -0.0000

Data Index: 352767 (C4 (Web Text))

Max Activating Token Index: 190

Text #14

Max Range: 1.8007. Min Range: -1.8007

Max Act: 0.8999. Min Act: -0.0000

Data Index: 754274 (C4 (Web Text))

Max Activating Token Index: 845

Text #15

Max Range: 1.8007. Min Range: -1.8007

Max Act: 0.8755. Min Act: -0.0000

Data Index: 1169369 (C4 (Web Text))

Max Activating Token Index: 410

Text #16

Max Range: 1.8007. Min Range: -1.8007

Max Act: 0.9176. Min Act: -0.0000

Data Index: 438027 (C4 (Web Text))

Max Activating Token Index: 530

Text #17

Max Range: 1.8007. Min Range: -1.8007

Max Act: 0.8061. Min Act: -0.0000

Data Index: 1156931 (C4 (Web Text))

Max Activating Token Index: 429

Text #18

Max Range: 1.8007. Min Range: -1.8007

Max Act: 0.8511. Min Act: 0.0000

Data Index: 49892 (C4 (Web Text))

Max Activating Token Index: 383

Text #19

Max Range: 1.8007. Min Range: -1.8007

Max Act: 0.8296. Min Act: -0.0000

Data Index: 141117 (C4 (Web Text))

Max Activating Token Index: 973