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

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

Neuron 2049 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0376. Min Act: -0.0003

Data Index: 225692 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0304. Min Act: -0.0003

Data Index: 450115 (C4 (Web Text))

Max Activating Token Index: 588

Text #2

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0295. Min Act: -0.0003

Data Index: 383628 (C4 (Web Text))

Max Activating Token Index: 807

Text #3

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0265. Min Act: -0.0003

Data Index: 853985 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0260. Min Act: -0.0003

Data Index: 104140 (C4 (Web Text))

Max Activating Token Index: 559

Text #5

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0259. Min Act: -0.0004

Data Index: 967687 (C4 (Web Text))

Max Activating Token Index: 557

Text #6

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0253. Min Act: -0.0003

Data Index: 99650 (C4 (Web Text))

Max Activating Token Index: 703

Text #7

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0262. Min Act: -0.0003

Data Index: 1214002 (C4 (Web Text))

Max Activating Token Index: 141

Text #8

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0244. Min Act: -0.0003

Data Index: 1109702 (C4 (Web Text))

Max Activating Token Index: 78

Text #9

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0249. Min Act: -0.0003

Data Index: 1142884 (C4 (Web Text))

Max Activating Token Index: 471

Text #10

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0246. Min Act: -0.0003

Data Index: 1262874 (C4 (Web Text))

Max Activating Token Index: 775

Text #11

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0250. Min Act: -0.0003

Data Index: 127132 (C4 (Web Text))

Max Activating Token Index: 394

Text #12

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0231. Min Act: -0.0003

Data Index: 590493 (C4 (Web Text))

Max Activating Token Index: 912

Text #13

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0241. Min Act: -0.0003

Data Index: 1047841 (C4 (Web Text))

Max Activating Token Index: 579

Text #14

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0240. Min Act: -0.0003

Data Index: 976639 (C4 (Web Text))

Max Activating Token Index: 959

Text #15

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0251. Min Act: -0.0003

Data Index: 552816 (C4 (Web Text))

Max Activating Token Index: 613

Text #16

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0239. Min Act: -0.0003

Data Index: 390768 (C4 (Web Text))

Max Activating Token Index: 490

Text #17

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0239. Min Act: -0.0003

Data Index: 735947 (C4 (Web Text))

Max Activating Token Index: 900

Text #18

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0230. Min Act: -0.0003

Data Index: 1358066 (C4 (Web Text))

Max Activating Token Index: 1002

Text #19

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0239. Min Act: -0.0003

Data Index: 187669 (C4 (Web Text))

Max Activating Token Index: 171