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

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

Neuron 3960 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1243. Min Range: -1.1243

Max Act: 1.1243. Min Act: -0.0001

Data Index: 154809 (C4 (Web Text))

Max Activating Token Index: 67

Text #1

Max Range: 1.1243. Min Range: -1.1243

Max Act: 1.0348. Min Act: -0.0001

Data Index: 506035 (C4 (Web Text))

Max Activating Token Index: 891

Text #2

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.9231. Min Act: -0.0001

Data Index: 499221 (C4 (Web Text))

Max Activating Token Index: 573

Text #3

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.9733. Min Act: -0.0001

Data Index: 402316 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.9002. Min Act: -0.0001

Data Index: 1229800 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.8653. Min Act: -0.0001

Data Index: 410681 (C4 (Web Text))

Max Activating Token Index: 775

Text #6

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.9139. Min Act: -0.0001

Data Index: 36650 (C4 (Web Text))

Max Activating Token Index: 438

Text #7

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.9368. Min Act: -0.0001

Data Index: 576295 (C4 (Web Text))

Max Activating Token Index: 658

Text #8

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.8689. Min Act: -0.0001

Data Index: 324171 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.8707. Min Act: -0.0001

Data Index: 988433 (C4 (Web Text))

Max Activating Token Index: 853

Text #10

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.8416. Min Act: -0.0001

Data Index: 964021 (C4 (Web Text))

Max Activating Token Index: 346

Text #11

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.8372. Min Act: -0.0001

Data Index: 1100829 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.8278. Min Act: -0.0001

Data Index: 1136432 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.8247. Min Act: -0.0001

Data Index: 961077 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.8322. Min Act: -0.0001

Data Index: 1133245 (C4 (Web Text))

Max Activating Token Index: 584

Text #15

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.8314. Min Act: -0.0001

Data Index: 1189525 (C4 (Web Text))

Max Activating Token Index: 758

Text #16

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.7860. Min Act: -0.0001

Data Index: 297772 (C4 (Web Text))

Max Activating Token Index: 305

Text #17

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.8525. Min Act: -0.0001

Data Index: 290638 (C4 (Web Text))

Max Activating Token Index: 120

Text #18

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.7941. Min Act: -0.0001

Data Index: 988 (C4 (Web Text))

Max Activating Token Index: 628

Text #19

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.8183. Min Act: -0.0001

Data Index: 485338 (C4 (Web Text))

Max Activating Token Index: 997