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

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

Neuron 6038 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: 5.4138. Min Range: -5.4138

Max Act: 5.4138. Min Act: -0.0000

Data Index: 616652 (C4 (Web Text))

Max Activating Token Index: 796

Text #1

Max Range: 5.4138. Min Range: -5.4138

Max Act: 4.5764. Min Act: -0.0000

Data Index: 1221475 (C4 (Web Text))

Max Activating Token Index: 346

Text #2

Max Range: 5.4138. Min Range: -5.4138

Max Act: 4.0625. Min Act: -0.0000

Data Index: 852452 (C4 (Web Text))

Max Activating Token Index: 982

Text #3

Max Range: 5.4138. Min Range: -5.4138

Max Act: 4.2366. Min Act: -0.0000

Data Index: 761005 (C4 (Web Text))

Max Activating Token Index: 643

Text #4

Max Range: 5.4138. Min Range: -5.4138

Max Act: 4.4933. Min Act: -0.0000

Data Index: 892268 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 5.4138. Min Range: -5.4138

Max Act: 4.2251. Min Act: -0.0000

Data Index: 668430 (C4 (Web Text))

Max Activating Token Index: 660

Text #6

Max Range: 5.4138. Min Range: -5.4138

Max Act: 4.5737. Min Act: -0.0000

Data Index: 641775 (C4 (Web Text))

Max Activating Token Index: 234

Text #7

Max Range: 5.4138. Min Range: -5.4138

Max Act: 4.1862. Min Act: -0.0000

Data Index: 844397 (C4 (Web Text))

Max Activating Token Index: 107

Text #8

Max Range: 5.4138. Min Range: -5.4138

Max Act: 4.0092. Min Act: -0.0000

Data Index: 62670 (C4 (Web Text))

Max Activating Token Index: 921

Text #9

Max Range: 5.4138. Min Range: -5.4138

Max Act: 4.3292. Min Act: -0.0000

Data Index: 7045 (C4 (Web Text))

Max Activating Token Index: 1007

Text #10

Max Range: 5.4138. Min Range: -5.4138

Max Act: 4.1314. Min Act: -0.0000

Data Index: 1148173 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 5.4138. Min Range: -5.4138

Max Act: 3.8321. Min Act: -0.0000

Data Index: 259398 (C4 (Web Text))

Max Activating Token Index: 813

Text #12

Max Range: 5.4138. Min Range: -5.4138

Max Act: 4.0717. Min Act: -0.0000

Data Index: 875022 (C4 (Web Text))

Max Activating Token Index: 257

Text #13

Max Range: 5.4138. Min Range: -5.4138

Max Act: 4.2129. Min Act: -0.0000

Data Index: 1007849 (C4 (Web Text))

Max Activating Token Index: 50

Text #14

Max Range: 5.4138. Min Range: -5.4138

Max Act: 4.1919. Min Act: -0.0000

Data Index: 996098 (C4 (Web Text))

Max Activating Token Index: 310

Text #15

Max Range: 5.4138. Min Range: -5.4138

Max Act: 4.3309. Min Act: -0.0000

Data Index: 1322470 (C4 (Web Text))

Max Activating Token Index: 559

Text #16

Max Range: 5.4138. Min Range: -5.4138

Max Act: 3.9426. Min Act: -0.0000

Data Index: 241295 (C4 (Web Text))

Max Activating Token Index: 804

Text #17

Max Range: 5.4138. Min Range: -5.4138

Max Act: 3.9067. Min Act: -0.0000

Data Index: 187408 (C4 (Web Text))

Max Activating Token Index: 253

Text #18

Max Range: 5.4138. Min Range: -5.4138

Max Act: 4.0704. Min Act: -0.0000

Data Index: 1094031 (C4 (Web Text))

Max Activating Token Index: 897

Text #19

Max Range: 5.4138. Min Range: -5.4138

Max Act: 3.8848. Min Act: -0.0000

Data Index: 1006496 (C4 (Web Text))

Max Activating Token Index: 242