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

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

Neuron 2485 in Layer 5

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: -0.0001

Data Index: 1293015 (C4 (Web Text))

Max Activating Token Index: 633

Text #1

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0313. Min Act: -0.0001

Data Index: 881466 (C4 (Web Text))

Max Activating Token Index: 510

Text #2

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0278. Min Act: -0.0000

Data Index: 819898 (C4 (Web Text))

Max Activating Token Index: 787

Text #3

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0273. Min Act: -0.0000

Data Index: 713845 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0256. Min Act: -0.0000

Data Index: 809162 (C4 (Web Text))

Max Activating Token Index: 347

Text #5

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0248. Min Act: -0.0001

Data Index: 597347 (C4 (Web Text))

Max Activating Token Index: 430

Text #6

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0212. Min Act: -0.0001

Data Index: 750083 (C4 (Web Text))

Max Activating Token Index: 695

Text #7

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0229. Min Act: -0.0000

Data Index: 1189860 (C4 (Web Text))

Max Activating Token Index: 557

Text #8

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0214. Min Act: -0.0000

Data Index: 1275293 (C4 (Web Text))

Max Activating Token Index: 305

Text #9

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0223. Min Act: -0.0001

Data Index: 249731 (C4 (Web Text))

Max Activating Token Index: 1015

Text #10

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0211. Min Act: -0.0000

Data Index: 1445988 (Python Code)

Max Activating Token Index: 163

Text #11

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0199. Min Act: -0.0001

Data Index: 748686 (C4 (Web Text))

Max Activating Token Index: 976

Text #12

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0198. Min Act: -0.0000

Data Index: 1053932 (C4 (Web Text))

Max Activating Token Index: 299

Text #13

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0191. Min Act: -0.0001

Data Index: 560641 (C4 (Web Text))

Max Activating Token Index: 562

Text #14

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0202. Min Act: -0.0001

Data Index: 399024 (C4 (Web Text))

Max Activating Token Index: 600

Text #15

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0194. Min Act: -0.0001

Data Index: 187506 (C4 (Web Text))

Max Activating Token Index: 882

Text #16

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0196. Min Act: -0.0000

Data Index: 1235653 (C4 (Web Text))

Max Activating Token Index: 884

Text #17

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0198. Min Act: -0.0001

Data Index: 1090872 (C4 (Web Text))

Max Activating Token Index: 640

Text #18

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0197. Min Act: -0.0000

Data Index: 1147703 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0219. Min Act: -0.0001

Data Index: 102077 (C4 (Web Text))

Max Activating Token Index: 170