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

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

Neuron 5591 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0268. Min Range: -1.0268

Max Act: 1.0268. Min Act: -0.0000

Data Index: 1055921 (C4 (Web Text))

Max Activating Token Index: 603

Text #1

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.7373. Min Act: -0.0000

Data Index: 1063610 (C4 (Web Text))

Max Activating Token Index: 310

Text #2

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.7185. Min Act: -0.0000

Data Index: 113240 (C4 (Web Text))

Max Activating Token Index: 684

Text #3

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.7346. Min Act: -0.0000

Data Index: 1003920 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.7579. Min Act: -0.0000

Data Index: 536586 (C4 (Web Text))

Max Activating Token Index: 881

Text #5

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.6836. Min Act: -0.0000

Data Index: 570749 (C4 (Web Text))

Max Activating Token Index: 468

Text #6

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.7143. Min Act: -0.0000

Data Index: 903632 (C4 (Web Text))

Max Activating Token Index: 488

Text #7

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.6222. Min Act: -0.0000

Data Index: 1191766 (C4 (Web Text))

Max Activating Token Index: 624

Text #8

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.6394. Min Act: -0.0000

Data Index: 312856 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.6193. Min Act: -0.0000

Data Index: 394827 (C4 (Web Text))

Max Activating Token Index: 984

Text #10

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.6041. Min Act: -0.0000

Data Index: 975239 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.6428. Min Act: -0.0000

Data Index: 898132 (C4 (Web Text))

Max Activating Token Index: 406

Text #12

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.6896. Min Act: -0.0000

Data Index: 477721 (C4 (Web Text))

Max Activating Token Index: 391

Text #13

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.6309. Min Act: -0.0000

Data Index: 202621 (C4 (Web Text))

Max Activating Token Index: 315

Text #14

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.6224. Min Act: -0.0000

Data Index: 641289 (C4 (Web Text))

Max Activating Token Index: 507

Text #15

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.5962. Min Act: -0.0000

Data Index: 1187212 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.6063. Min Act: -0.0000

Data Index: 1062118 (C4 (Web Text))

Max Activating Token Index: 634

Text #17

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.6254. Min Act: -0.0000

Data Index: 978094 (C4 (Web Text))

Max Activating Token Index: 87

Text #18

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.6264. Min Act: -0.0000

Data Index: 87852 (C4 (Web Text))

Max Activating Token Index: 199

Text #19

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.6083. Min Act: -0.0000

Data Index: 383399 (C4 (Web Text))

Max Activating Token Index: 794