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

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

Neuron 4742 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0589. Min Range: -1.0589

Max Act: 1.0589. Min Act: -0.0000

Data Index: 1318184 (C4 (Web Text))

Max Activating Token Index: 807

Text #1

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.8219. Min Act: -0.0000

Data Index: 401132 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.8453. Min Act: -0.0000

Data Index: 1201236 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.8469. Min Act: -0.0000

Data Index: 378608 (C4 (Web Text))

Max Activating Token Index: 1022

Text #4

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.7885. Min Act: -0.0000

Data Index: 749809 (C4 (Web Text))

Max Activating Token Index: 97

Text #5

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.8111. Min Act: -0.0000

Data Index: 965885 (C4 (Web Text))

Max Activating Token Index: 791

Text #6

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.7901. Min Act: -0.0000

Data Index: 263661 (C4 (Web Text))

Max Activating Token Index: 876

Text #7

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.7645. Min Act: -0.0000

Data Index: 123615 (C4 (Web Text))

Max Activating Token Index: 248

Text #8

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.7394. Min Act: -0.0000

Data Index: 507497 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.6984. Min Act: -0.0000

Data Index: 491986 (C4 (Web Text))

Max Activating Token Index: 841

Text #10

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.7368. Min Act: -0.0000

Data Index: 490308 (C4 (Web Text))

Max Activating Token Index: 876

Text #11

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.7127. Min Act: -0.0000

Data Index: 431401 (C4 (Web Text))

Max Activating Token Index: 940

Text #12

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.7055. Min Act: -0.0000

Data Index: 70791 (C4 (Web Text))

Max Activating Token Index: 904

Text #13

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.7272. Min Act: -0.0000

Data Index: 394169 (C4 (Web Text))

Max Activating Token Index: 169

Text #14

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.7243. Min Act: -0.0000

Data Index: 1028789 (C4 (Web Text))

Max Activating Token Index: 924

Text #15

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.7028. Min Act: -0.0000

Data Index: 1309514 (C4 (Web Text))

Max Activating Token Index: 537

Text #16

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.7193. Min Act: -0.0000

Data Index: 1205010 (C4 (Web Text))

Max Activating Token Index: 263

Text #17

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.7191. Min Act: -0.0000

Data Index: 824381 (C4 (Web Text))

Max Activating Token Index: 356

Text #18

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.7135. Min Act: -0.0000

Data Index: 944567 (C4 (Web Text))

Max Activating Token Index: 216

Text #19

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.6851. Min Act: -0.0000

Data Index: 561814 (C4 (Web Text))

Max Activating Token Index: 156