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

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

Neuron 840 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8186. Min Range: -0.8186

Max Act: 0.8186. Min Act: -0.0003

Data Index: 477793 (C4 (Web Text))

Max Activating Token Index: 398

Text #1

Max Range: 0.8186. Min Range: -0.8186

Max Act: 0.7788. Min Act: -0.0003

Data Index: 1013320 (C4 (Web Text))

Max Activating Token Index: 669

Text #2

Max Range: 0.8186. Min Range: -0.8186

Max Act: 0.7799. Min Act: -0.0003

Data Index: 638768 (C4 (Web Text))

Max Activating Token Index: 425

Text #3

Max Range: 0.8186. Min Range: -0.8186

Max Act: 0.7533. Min Act: -0.0002

Data Index: 822056 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 0.8186. Min Range: -0.8186

Max Act: 0.7461. Min Act: -0.0002

Data Index: 697241 (C4 (Web Text))

Max Activating Token Index: 151

Text #5

Max Range: 0.8186. Min Range: -0.8186

Max Act: 0.6644. Min Act: -0.0002

Data Index: 142499 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 0.8186. Min Range: -0.8186

Max Act: 0.6589. Min Act: -0.0002

Data Index: 114732 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 0.8186. Min Range: -0.8186

Max Act: 0.6429. Min Act: -0.0003

Data Index: 655104 (C4 (Web Text))

Max Activating Token Index: 875

Text #8

Max Range: 0.8186. Min Range: -0.8186

Max Act: 0.6639. Min Act: -0.0003

Data Index: 1114620 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 0.8186. Min Range: -0.8186

Max Act: 0.6494. Min Act: -0.0002

Data Index: 60815 (C4 (Web Text))

Max Activating Token Index: 875

Text #10

Max Range: 0.8186. Min Range: -0.8186

Max Act: 0.6483. Min Act: -0.0002

Data Index: 618680 (C4 (Web Text))

Max Activating Token Index: 236

Text #11

Max Range: 0.8186. Min Range: -0.8186

Max Act: 0.6444. Min Act: -0.0002

Data Index: 1092005 (C4 (Web Text))

Max Activating Token Index: 497

Text #12

Max Range: 0.8186. Min Range: -0.8186

Max Act: 0.6155. Min Act: -0.0002

Data Index: 847896 (C4 (Web Text))

Max Activating Token Index: 822

Text #13

Max Range: 0.8186. Min Range: -0.8186

Max Act: 0.6336. Min Act: -0.0003

Data Index: 1304503 (C4 (Web Text))

Max Activating Token Index: 283

Text #14

Max Range: 0.8186. Min Range: -0.8186

Max Act: 0.6279. Min Act: -0.0002

Data Index: 315258 (C4 (Web Text))

Max Activating Token Index: 173

Text #15

Max Range: 0.8186. Min Range: -0.8186

Max Act: 0.6261. Min Act: -0.0002

Data Index: 1107962 (C4 (Web Text))

Max Activating Token Index: 650

Text #16

Max Range: 0.8186. Min Range: -0.8186

Max Act: 0.6137. Min Act: -0.0002

Data Index: 570847 (C4 (Web Text))

Max Activating Token Index: 92

Text #17

Max Range: 0.8186. Min Range: -0.8186

Max Act: 0.6115. Min Act: -0.0002

Data Index: 911165 (C4 (Web Text))

Max Activating Token Index: 290

Text #18

Max Range: 0.8186. Min Range: -0.8186

Max Act: 0.6100. Min Act: -0.0003

Data Index: 262854 (C4 (Web Text))

Max Activating Token Index: 154

Text #19

Max Range: 0.8186. Min Range: -0.8186

Max Act: 0.6094. Min Act: -0.0002

Data Index: 637148 (C4 (Web Text))

Max Activating Token Index: 211