Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3637 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.0402. Min Range: -4.0402

Max Act: 3.9327. Min Act: -0.0000

Data Index: 257080 (C4 (Web Text))

Max Activating Token Index: 847

Text #1

Max Range: 4.0402. Min Range: -4.0402

Max Act: 4.0402. Min Act: -0.0000

Data Index: 1339367 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 4.0402. Min Range: -4.0402

Max Act: 3.4675. Min Act: -0.0000

Data Index: 624172 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 4.0402. Min Range: -4.0402

Max Act: 3.3077. Min Act: -0.0000

Data Index: 1125356 (C4 (Web Text))

Max Activating Token Index: 463

Text #4

Max Range: 4.0402. Min Range: -4.0402

Max Act: 3.1138. Min Act: -0.0000

Data Index: 730148 (C4 (Web Text))

Max Activating Token Index: 746

Text #5

Max Range: 4.0402. Min Range: -4.0402

Max Act: 3.1168. Min Act: -0.0000

Data Index: 975338 (C4 (Web Text))

Max Activating Token Index: 521

Text #6

Max Range: 4.0402. Min Range: -4.0402

Max Act: 3.2729. Min Act: -0.0000

Data Index: 759349 (C4 (Web Text))

Max Activating Token Index: 287

Text #7

Max Range: 4.0402. Min Range: -4.0402

Max Act: 3.0038. Min Act: -0.0000

Data Index: 490325 (C4 (Web Text))

Max Activating Token Index: 424

Text #8

Max Range: 4.0402. Min Range: -4.0402

Max Act: 3.0509. Min Act: -0.0000

Data Index: 1224380 (C4 (Web Text))

Max Activating Token Index: 26

Text #9

Max Range: 4.0402. Min Range: -4.0402

Max Act: 2.9517. Min Act: -0.0000

Data Index: 832236 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 4.0402. Min Range: -4.0402

Max Act: 2.9036. Min Act: -0.0000

Data Index: 168117 (C4 (Web Text))

Max Activating Token Index: 557

Text #11

Max Range: 4.0402. Min Range: -4.0402

Max Act: 2.8834. Min Act: -0.0000

Data Index: 253236 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 4.0402. Min Range: -4.0402

Max Act: 2.8553. Min Act: -0.0000

Data Index: 1246249 (C4 (Web Text))

Max Activating Token Index: 874

Text #13

Max Range: 4.0402. Min Range: -4.0402

Max Act: 2.8237. Min Act: -0.0000

Data Index: 1204712 (C4 (Web Text))

Max Activating Token Index: 505

Text #14

Max Range: 4.0402. Min Range: -4.0402

Max Act: 2.8226. Min Act: -0.0000

Data Index: 13383 (C4 (Web Text))

Max Activating Token Index: 411

Text #15

Max Range: 4.0402. Min Range: -4.0402

Max Act: 2.8954. Min Act: -0.0000

Data Index: 418082 (C4 (Web Text))

Max Activating Token Index: 16

Text #16

Max Range: 4.0402. Min Range: -4.0402

Max Act: 2.8682. Min Act: -0.0000

Data Index: 1277804 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 4.0402. Min Range: -4.0402

Max Act: 2.8695. Min Act: -0.0000

Data Index: 980293 (C4 (Web Text))

Max Activating Token Index: 268

Text #18

Max Range: 4.0402. Min Range: -4.0402

Max Act: 2.7207. Min Act: -0.0000

Data Index: 669376 (C4 (Web Text))

Max Activating Token Index: 662

Text #19

Max Range: 4.0402. Min Range: -4.0402

Max Act: 2.8217. Min Act: -0.0000

Data Index: 375004 (C4 (Web Text))

Max Activating Token Index: 110