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

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

Neuron 3551 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3823. Min Range: -0.3823

Max Act: 0.3823. Min Act: -0.0002

Data Index: 464312 (C4 (Web Text))

Max Activating Token Index: 367

Text #1

Max Range: 0.3823. Min Range: -0.3823

Max Act: 0.3507. Min Act: -0.0002

Data Index: 654002 (C4 (Web Text))

Max Activating Token Index: 485

Text #2

Max Range: 0.3823. Min Range: -0.3823

Max Act: 0.3344. Min Act: -0.0002

Data Index: 611548 (C4 (Web Text))

Max Activating Token Index: 387

Text #3

Max Range: 0.3823. Min Range: -0.3823

Max Act: 0.3299. Min Act: -0.0002

Data Index: 66826 (C4 (Web Text))

Max Activating Token Index: 369

Text #4

Max Range: 0.3823. Min Range: -0.3823

Max Act: 0.3154. Min Act: -0.0002

Data Index: 454315 (C4 (Web Text))

Max Activating Token Index: 245

Text #5

Max Range: 0.3823. Min Range: -0.3823

Max Act: 0.3251. Min Act: -0.0002

Data Index: 203987 (C4 (Web Text))

Max Activating Token Index: 652

Text #6

Max Range: 0.3823. Min Range: -0.3823

Max Act: 0.3333. Min Act: -0.0002

Data Index: 1202279 (C4 (Web Text))

Max Activating Token Index: 801

Text #7

Max Range: 0.3823. Min Range: -0.3823

Max Act: 0.3204. Min Act: -0.0002

Data Index: 871644 (C4 (Web Text))

Max Activating Token Index: 880

Text #8

Max Range: 0.3823. Min Range: -0.3823

Max Act: 0.3198. Min Act: -0.0002

Data Index: 783427 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 0.3823. Min Range: -0.3823

Max Act: 0.3178. Min Act: -0.0002

Data Index: 264975 (C4 (Web Text))

Max Activating Token Index: 225

Text #10

Max Range: 0.3823. Min Range: -0.3823

Max Act: 0.3179. Min Act: -0.0001

Data Index: 967145 (C4 (Web Text))

Max Activating Token Index: 478

Text #11

Max Range: 0.3823. Min Range: -0.3823

Max Act: 0.3169. Min Act: -0.0002

Data Index: 1331841 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 0.3823. Min Range: -0.3823

Max Act: 0.3027. Min Act: -0.0002

Data Index: 1321670 (C4 (Web Text))

Max Activating Token Index: 535

Text #13

Max Range: 0.3823. Min Range: -0.3823

Max Act: 0.3126. Min Act: -0.0002

Data Index: 985399 (C4 (Web Text))

Max Activating Token Index: 505

Text #14

Max Range: 0.3823. Min Range: -0.3823

Max Act: 0.3118. Min Act: -0.0002

Data Index: 653764 (C4 (Web Text))

Max Activating Token Index: 780

Text #15

Max Range: 0.3823. Min Range: -0.3823

Max Act: 0.3231. Min Act: -0.0002

Data Index: 727899 (C4 (Web Text))

Max Activating Token Index: 143

Text #16

Max Range: 0.3823. Min Range: -0.3823

Max Act: 0.3010. Min Act: -0.0002

Data Index: 139974 (C4 (Web Text))

Max Activating Token Index: 593

Text #17

Max Range: 0.3823. Min Range: -0.3823

Max Act: 0.3115. Min Act: -0.0002

Data Index: 1117538 (C4 (Web Text))

Max Activating Token Index: 403

Text #18

Max Range: 0.3823. Min Range: -0.3823

Max Act: 0.3113. Min Act: -0.0002

Data Index: 1285649 (C4 (Web Text))

Max Activating Token Index: 636

Text #19

Max Range: 0.3823. Min Range: -0.3823

Max Act: 0.2990. Min Act: -0.0002

Data Index: 572059 (C4 (Web Text))

Max Activating Token Index: 340