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

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

Neuron 3192 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3337. Min Range: -1.3337

Max Act: 1.2999. Min Act: -0.0001

Data Index: 819625 (C4 (Web Text))

Max Activating Token Index: 169

Text #1

Max Range: 1.3337. Min Range: -1.3337

Max Act: 1.3233. Min Act: -0.0000

Data Index: 1095572 (C4 (Web Text))

Max Activating Token Index: 758

Text #2

Max Range: 1.3337. Min Range: -1.3337

Max Act: 1.3337. Min Act: -0.0000

Data Index: 59162 (C4 (Web Text))

Max Activating Token Index: 834

Text #3

Max Range: 1.3337. Min Range: -1.3337

Max Act: 1.1114. Min Act: -0.0000

Data Index: 1076913 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 1.3337. Min Range: -1.3337

Max Act: 1.1355. Min Act: -0.0000

Data Index: 198143 (C4 (Web Text))

Max Activating Token Index: 511

Text #5

Max Range: 1.3337. Min Range: -1.3337

Max Act: 1.1278. Min Act: -0.0000

Data Index: 622868 (C4 (Web Text))

Max Activating Token Index: 708

Text #6

Max Range: 1.3337. Min Range: -1.3337

Max Act: 1.1852. Min Act: -0.0001

Data Index: 347889 (C4 (Web Text))

Max Activating Token Index: 791

Text #7

Max Range: 1.3337. Min Range: -1.3337

Max Act: 1.0838. Min Act: -0.0000

Data Index: 1357328 (C4 (Web Text))

Max Activating Token Index: 248

Text #8

Max Range: 1.3337. Min Range: -1.3337

Max Act: 1.0194. Min Act: -0.0000

Data Index: 1316231 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 1.3337. Min Range: -1.3337

Max Act: 1.0472. Min Act: -0.0000

Data Index: 960047 (C4 (Web Text))

Max Activating Token Index: 508

Text #10

Max Range: 1.3337. Min Range: -1.3337

Max Act: 1.0433. Min Act: -0.0000

Data Index: 957298 (C4 (Web Text))

Max Activating Token Index: 381

Text #11

Max Range: 1.3337. Min Range: -1.3337

Max Act: 0.9966. Min Act: -0.0000

Data Index: 1299908 (C4 (Web Text))

Max Activating Token Index: 531

Text #12

Max Range: 1.3337. Min Range: -1.3337

Max Act: 1.0446. Min Act: -0.0001

Data Index: 814570 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 1.3337. Min Range: -1.3337

Max Act: 0.9152. Min Act: -0.0000

Data Index: 983785 (C4 (Web Text))

Max Activating Token Index: 1017

Text #14

Max Range: 1.3337. Min Range: -1.3337

Max Act: 0.9911. Min Act: -0.0000

Data Index: 317985 (C4 (Web Text))

Max Activating Token Index: 54

Text #15

Max Range: 1.3337. Min Range: -1.3337

Max Act: 0.9575. Min Act: -0.0000

Data Index: 850744 (C4 (Web Text))

Max Activating Token Index: 955

Text #16

Max Range: 1.3337. Min Range: -1.3337

Max Act: 0.9906. Min Act: -0.0000

Data Index: 110483 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 1.3337. Min Range: -1.3337

Max Act: 0.9425. Min Act: -0.0001

Data Index: 870735 (C4 (Web Text))

Max Activating Token Index: 230

Text #18

Max Range: 1.3337. Min Range: -1.3337

Max Act: 0.9735. Min Act: -0.0000

Data Index: 658099 (C4 (Web Text))

Max Activating Token Index: 372

Text #19

Max Range: 1.3337. Min Range: -1.3337

Max Act: 0.9118. Min Act: -0.0000

Data Index: 8039 (C4 (Web Text))

Max Activating Token Index: 756