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

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

Neuron 20 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.3177. Min Act: -0.0000

Data Index: 260383 (C4 (Web Text))

Max Activating Token Index: 284

Text #1

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.3098. Min Act: -0.0000

Data Index: 1184016 (C4 (Web Text))

Max Activating Token Index: 149

Text #2

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.3027. Min Act: -0.0000

Data Index: 390846 (C4 (Web Text))

Max Activating Token Index: 717

Text #3

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2941. Min Act: -0.0000

Data Index: 629459 (C4 (Web Text))

Max Activating Token Index: 613

Text #4

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2569. Min Act: -0.0000

Data Index: 1274311 (C4 (Web Text))

Max Activating Token Index: 413

Text #5

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2609. Min Act: -0.0000

Data Index: 726545 (C4 (Web Text))

Max Activating Token Index: 394

Text #6

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2498. Min Act: -0.0000

Data Index: 1228199 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2351. Min Act: -0.0000

Data Index: 874864 (C4 (Web Text))

Max Activating Token Index: 780

Text #8

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2382. Min Act: -0.0000

Data Index: 115452 (C4 (Web Text))

Max Activating Token Index: 356

Text #9

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2232. Min Act: -0.0000

Data Index: 452242 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2380. Min Act: -0.0000

Data Index: 881352 (C4 (Web Text))

Max Activating Token Index: 658

Text #11

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2158. Min Act: -0.0000

Data Index: 1006354 (C4 (Web Text))

Max Activating Token Index: 492

Text #12

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2246. Min Act: -0.0000

Data Index: 62605 (C4 (Web Text))

Max Activating Token Index: 429

Text #13

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2154. Min Act: -0.0000

Data Index: 826680 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2226. Min Act: -0.0000

Data Index: 587813 (C4 (Web Text))

Max Activating Token Index: 488

Text #15

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2214. Min Act: -0.0000

Data Index: 320817 (C4 (Web Text))

Max Activating Token Index: 349

Text #16

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2194. Min Act: -0.0000

Data Index: 927951 (C4 (Web Text))

Max Activating Token Index: 955

Text #17

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2049. Min Act: -0.0001

Data Index: 348780 (C4 (Web Text))

Max Activating Token Index: 475

Text #18

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2197. Min Act: -0.0000

Data Index: 1177603 (C4 (Web Text))

Max Activating Token Index: 21

Text #19

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2187. Min Act: -0.0000

Data Index: 441352 (C4 (Web Text))

Max Activating Token Index: 538