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

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

Neuron 3523 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: 4.5221. Min Range: -4.5221

Max Act: 4.5221. Min Act: -0.0000

Data Index: 902883 (C4 (Web Text))

Max Activating Token Index: 173

Text #1

Max Range: 4.5221. Min Range: -4.5221

Max Act: 3.5441. Min Act: -0.0000

Data Index: 28118 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 4.5221. Min Range: -4.5221

Max Act: 3.5358. Min Act: -0.0000

Data Index: 916213 (C4 (Web Text))

Max Activating Token Index: 509

Text #3

Max Range: 4.5221. Min Range: -4.5221

Max Act: 3.3470. Min Act: -0.0000

Data Index: 863532 (C4 (Web Text))

Max Activating Token Index: 405

Text #4

Max Range: 4.5221. Min Range: -4.5221

Max Act: 3.4395. Min Act: -0.0000

Data Index: 492436 (C4 (Web Text))

Max Activating Token Index: 250

Text #5

Max Range: 4.5221. Min Range: -4.5221

Max Act: 3.0338. Min Act: -0.0000

Data Index: 1219525 (C4 (Web Text))

Max Activating Token Index: 579

Text #6

Max Range: 4.5221. Min Range: -4.5221

Max Act: 2.9443. Min Act: -0.0000

Data Index: 792058 (C4 (Web Text))

Max Activating Token Index: 358

Text #7

Max Range: 4.5221. Min Range: -4.5221

Max Act: 2.7800. Min Act: -0.0000

Data Index: 1229143 (C4 (Web Text))

Max Activating Token Index: 780

Text #8

Max Range: 4.5221. Min Range: -4.5221

Max Act: 2.6824. Min Act: -0.0000

Data Index: 422761 (C4 (Web Text))

Max Activating Token Index: 853

Text #9

Max Range: 4.5221. Min Range: -4.5221

Max Act: 2.8182. Min Act: -0.0000

Data Index: 1145527 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 4.5221. Min Range: -4.5221

Max Act: 2.7689. Min Act: -0.0000

Data Index: 86465 (C4 (Web Text))

Max Activating Token Index: 369

Text #11

Max Range: 4.5221. Min Range: -4.5221

Max Act: 2.7769. Min Act: -0.0000

Data Index: 474040 (C4 (Web Text))

Max Activating Token Index: 592

Text #12

Max Range: 4.5221. Min Range: -4.5221

Max Act: 2.7385. Min Act: -0.0000

Data Index: 538323 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 4.5221. Min Range: -4.5221

Max Act: 2.7381. Min Act: -0.0000

Data Index: 608882 (C4 (Web Text))

Max Activating Token Index: 135

Text #14

Max Range: 4.5221. Min Range: -4.5221

Max Act: 2.9546. Min Act: -0.0000

Data Index: 669049 (C4 (Web Text))

Max Activating Token Index: 750

Text #15

Max Range: 4.5221. Min Range: -4.5221

Max Act: 2.7098. Min Act: -0.0000

Data Index: 594437 (C4 (Web Text))

Max Activating Token Index: 453

Text #16

Max Range: 4.5221. Min Range: -4.5221

Max Act: 2.6732. Min Act: -0.0000

Data Index: 610372 (C4 (Web Text))

Max Activating Token Index: 712

Text #17

Max Range: 4.5221. Min Range: -4.5221

Max Act: 2.5326. Min Act: -0.0000

Data Index: 183391 (C4 (Web Text))

Max Activating Token Index: 228

Text #18

Max Range: 4.5221. Min Range: -4.5221

Max Act: 2.5234. Min Act: -0.0000

Data Index: 107437 (C4 (Web Text))

Max Activating Token Index: 217

Text #19

Max Range: 4.5221. Min Range: -4.5221

Max Act: 2.6186. Min Act: -0.0000

Data Index: 1213162 (C4 (Web Text))

Max Activating Token Index: 742