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

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

Neuron 1590 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: 0.0324. Min Range: -0.0324

Max Act: 0.0324. Min Act: -0.0003

Data Index: 489642 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0306. Min Act: -0.0003

Data Index: 203695 (C4 (Web Text))

Max Activating Token Index: 377

Text #2

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0290. Min Act: -0.0003

Data Index: 81581 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0286. Min Act: -0.0003

Data Index: 127320 (C4 (Web Text))

Max Activating Token Index: 403

Text #4

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0265. Min Act: -0.0003

Data Index: 707710 (C4 (Web Text))

Max Activating Token Index: 387

Text #5

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0286. Min Act: -0.0003

Data Index: 408276 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0279. Min Act: -0.0003

Data Index: 1274361 (C4 (Web Text))

Max Activating Token Index: 988

Text #7

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0269. Min Act: -0.0003

Data Index: 1021202 (C4 (Web Text))

Max Activating Token Index: 6

Text #8

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0266. Min Act: -0.0003

Data Index: 908415 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0264. Min Act: -0.0003

Data Index: 192842 (C4 (Web Text))

Max Activating Token Index: 985

Text #10

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0251. Min Act: -0.0003

Data Index: 1031748 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0262. Min Act: -0.0003

Data Index: 890047 (C4 (Web Text))

Max Activating Token Index: 674

Text #12

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0262. Min Act: -0.0003

Data Index: 174858 (C4 (Web Text))

Max Activating Token Index: 365

Text #13

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0261. Min Act: -0.0003

Data Index: 713443 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0265. Min Act: -0.0003

Data Index: 527416 (C4 (Web Text))

Max Activating Token Index: 308

Text #15

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0260. Min Act: -0.0003

Data Index: 925827 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0263. Min Act: -0.0003

Data Index: 996672 (C4 (Web Text))

Max Activating Token Index: 601

Text #17

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0247. Min Act: -0.0003

Data Index: 843825 (C4 (Web Text))

Max Activating Token Index: 210

Text #18

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0268. Min Act: -0.0003

Data Index: 940714 (C4 (Web Text))

Max Activating Token Index: 372

Text #19

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0238. Min Act: -0.0003

Data Index: 565172 (C4 (Web Text))

Max Activating Token Index: 344