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

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

Neuron 3946 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.8568. Min Act: 0.0000

Data Index: 846222 (C4 (Web Text))

Max Activating Token Index: 848

Text #1

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.9214. Min Act: -0.0000

Data Index: 45634 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.8275. Min Act: -0.0000

Data Index: 507916 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.8477. Min Act: -0.0000

Data Index: 596015 (C4 (Web Text))

Max Activating Token Index: 359

Text #4

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.7620. Min Act: -0.0000

Data Index: 464939 (C4 (Web Text))

Max Activating Token Index: 656

Text #5

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.7421. Min Act: -0.0000

Data Index: 792955 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.6738. Min Act: -0.0000

Data Index: 1071647 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.6787. Min Act: -0.0000

Data Index: 119675 (C4 (Web Text))

Max Activating Token Index: 1003

Text #8

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.7264. Min Act: -0.0000

Data Index: 305944 (C4 (Web Text))

Max Activating Token Index: 404

Text #9

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.6693. Min Act: -0.0000

Data Index: 883396 (C4 (Web Text))

Max Activating Token Index: 307

Text #10

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.6722. Min Act: -0.0000

Data Index: 276273 (C4 (Web Text))

Max Activating Token Index: 300

Text #11

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.6684. Min Act: -0.0000

Data Index: 579799 (C4 (Web Text))

Max Activating Token Index: 213

Text #12

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.6763. Min Act: -0.0000

Data Index: 126412 (C4 (Web Text))

Max Activating Token Index: 193

Text #13

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.6246. Min Act: -0.0000

Data Index: 783294 (C4 (Web Text))

Max Activating Token Index: 508

Text #14

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.6216. Min Act: -0.0000

Data Index: 722034 (C4 (Web Text))

Max Activating Token Index: 32

Text #15

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.6491. Min Act: 0.0001

Data Index: 451405 (C4 (Web Text))

Max Activating Token Index: 244

Text #16

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.6172. Min Act: -0.0000

Data Index: 469023 (C4 (Web Text))

Max Activating Token Index: 841

Text #17

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.6088. Min Act: -0.0000

Data Index: 763235 (C4 (Web Text))

Max Activating Token Index: 396

Text #18

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.6330. Min Act: -0.0000

Data Index: 972218 (C4 (Web Text))

Max Activating Token Index: 297

Text #19

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.5949. Min Act: 0.0001

Data Index: 782532 (C4 (Web Text))

Max Activating Token Index: 57