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

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

Neuron 917 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: 1.5235. Min Range: -1.5235

Max Act: 1.5235. Min Act: -0.0001

Data Index: 903571 (C4 (Web Text))

Max Activating Token Index: 733

Text #1

Max Range: 1.5235. Min Range: -1.5235

Max Act: 1.5100. Min Act: -0.0001

Data Index: 543472 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 1.5235. Min Range: -1.5235

Max Act: 1.4145. Min Act: -0.0001

Data Index: 752375 (C4 (Web Text))

Max Activating Token Index: 838

Text #3

Max Range: 1.5235. Min Range: -1.5235

Max Act: 1.4845. Min Act: -0.0001

Data Index: 1218021 (C4 (Web Text))

Max Activating Token Index: 73

Text #4

Max Range: 1.5235. Min Range: -1.5235

Max Act: 1.4633. Min Act: -0.0001

Data Index: 1028404 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 1.5235. Min Range: -1.5235

Max Act: 1.4597. Min Act: -0.0001

Data Index: 525868 (C4 (Web Text))

Max Activating Token Index: 422

Text #6

Max Range: 1.5235. Min Range: -1.5235

Max Act: 1.4556. Min Act: -0.0001

Data Index: 1108782 (C4 (Web Text))

Max Activating Token Index: 6

Text #7

Max Range: 1.5235. Min Range: -1.5235

Max Act: 1.4483. Min Act: -0.0001

Data Index: 145261 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 1.5235. Min Range: -1.5235

Max Act: 1.4196. Min Act: -0.0001

Data Index: 1179305 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 1.5235. Min Range: -1.5235

Max Act: 1.3741. Min Act: -0.0001

Data Index: 1190495 (C4 (Web Text))

Max Activating Token Index: 666

Text #10

Max Range: 1.5235. Min Range: -1.5235

Max Act: 1.3362. Min Act: -0.0001

Data Index: 40157 (C4 (Web Text))

Max Activating Token Index: 552

Text #11

Max Range: 1.5235. Min Range: -1.5235

Max Act: 1.3631. Min Act: -0.0001

Data Index: 716672 (C4 (Web Text))

Max Activating Token Index: 425

Text #12

Max Range: 1.5235. Min Range: -1.5235

Max Act: 1.3527. Min Act: -0.0001

Data Index: 209965 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 1.5235. Min Range: -1.5235

Max Act: 1.3194. Min Act: -0.0001

Data Index: 191679 (C4 (Web Text))

Max Activating Token Index: 403

Text #14

Max Range: 1.5235. Min Range: -1.5235

Max Act: 1.3385. Min Act: -0.0001

Data Index: 1091303 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 1.5235. Min Range: -1.5235

Max Act: 1.3338. Min Act: -0.0001

Data Index: 219460 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 1.5235. Min Range: -1.5235

Max Act: 1.3217. Min Act: -0.0001

Data Index: 941012 (C4 (Web Text))

Max Activating Token Index: 15

Text #17

Max Range: 1.5235. Min Range: -1.5235

Max Act: 1.3197. Min Act: -0.0001

Data Index: 349521 (C4 (Web Text))

Max Activating Token Index: 384

Text #18

Max Range: 1.5235. Min Range: -1.5235

Max Act: 1.3182. Min Act: -0.0001

Data Index: 1140887 (C4 (Web Text))

Max Activating Token Index: 171

Text #19

Max Range: 1.5235. Min Range: -1.5235

Max Act: 1.2752. Min Act: -0.0001

Data Index: 1221260 (C4 (Web Text))

Max Activating Token Index: 173