Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 710 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0218. Min Act: -0.0006

Data Index: 939161 (C4 (Web Text))

Max Activating Token Index: 454

Text #1

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0212. Min Act: -0.0006

Data Index: 662259 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0193. Min Act: -0.0006

Data Index: 296523 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0200. Min Act: -0.0006

Data Index: 182613 (C4 (Web Text))

Max Activating Token Index: 609

Text #4

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0196. Min Act: -0.0006

Data Index: 202349 (C4 (Web Text))

Max Activating Token Index: 607

Text #5

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0197. Min Act: -0.0006

Data Index: 25269 (C4 (Web Text))

Max Activating Token Index: 965

Text #6

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0191. Min Act: -0.0006

Data Index: 1169051 (C4 (Web Text))

Max Activating Token Index: 437

Text #7

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0191. Min Act: -0.0006

Data Index: 487564 (C4 (Web Text))

Max Activating Token Index: 437

Text #8

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0195. Min Act: -0.0006

Data Index: 18522 (C4 (Web Text))

Max Activating Token Index: 784

Text #9

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0193. Min Act: -0.0006

Data Index: 88519 (C4 (Web Text))

Max Activating Token Index: 777

Text #10

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0181. Min Act: -0.0006

Data Index: 823074 (C4 (Web Text))

Max Activating Token Index: 692

Text #11

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0199. Min Act: -0.0006

Data Index: 219836 (C4 (Web Text))

Max Activating Token Index: 720

Text #12

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0177. Min Act: -0.0006

Data Index: 744335 (C4 (Web Text))

Max Activating Token Index: 169

Text #13

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0184. Min Act: -0.0006

Data Index: 829617 (C4 (Web Text))

Max Activating Token Index: 816

Text #14

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0176. Min Act: -0.0005

Data Index: 859579 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0179. Min Act: -0.0006

Data Index: 846805 (C4 (Web Text))

Max Activating Token Index: 582

Text #16

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0177. Min Act: -0.0005

Data Index: 487823 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0184. Min Act: -0.0006

Data Index: 1151845 (C4 (Web Text))

Max Activating Token Index: 621

Text #18

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0177. Min Act: -0.0006

Data Index: 36500 (C4 (Web Text))

Max Activating Token Index: 629

Text #19

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0176. Min Act: -0.0006

Data Index: 938848 (C4 (Web Text))

Max Activating Token Index: 881