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

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

Neuron 3418 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4237. Min Range: -1.4237

Max Act: 1.4237. Min Act: -0.0001

Data Index: 567931 (C4 (Web Text))

Max Activating Token Index: 429

Text #1

Max Range: 1.4237. Min Range: -1.4237

Max Act: 1.2562. Min Act: -0.0000

Data Index: 1201237 (C4 (Web Text))

Max Activating Token Index: 274

Text #2

Max Range: 1.4237. Min Range: -1.4237

Max Act: 1.1892. Min Act: -0.0000

Data Index: 28660 (C4 (Web Text))

Max Activating Token Index: 426

Text #3

Max Range: 1.4237. Min Range: -1.4237

Max Act: 1.1822. Min Act: -0.0000

Data Index: 50217 (C4 (Web Text))

Max Activating Token Index: 944

Text #4

Max Range: 1.4237. Min Range: -1.4237

Max Act: 1.1407. Min Act: -0.0000

Data Index: 996205 (C4 (Web Text))

Max Activating Token Index: 922

Text #5

Max Range: 1.4237. Min Range: -1.4237

Max Act: 1.1818. Min Act: -0.0000

Data Index: 323998 (C4 (Web Text))

Max Activating Token Index: 393

Text #6

Max Range: 1.4237. Min Range: -1.4237

Max Act: 1.0373. Min Act: -0.0001

Data Index: 264842 (C4 (Web Text))

Max Activating Token Index: 691

Text #7

Max Range: 1.4237. Min Range: -1.4237

Max Act: 1.0362. Min Act: -0.0001

Data Index: 732149 (C4 (Web Text))

Max Activating Token Index: 403

Text #8

Max Range: 1.4237. Min Range: -1.4237

Max Act: 0.9934. Min Act: -0.0000

Data Index: 529033 (C4 (Web Text))

Max Activating Token Index: 597

Text #9

Max Range: 1.4237. Min Range: -1.4237

Max Act: 1.0188. Min Act: -0.0000

Data Index: 236410 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 1.4237. Min Range: -1.4237

Max Act: 1.0265. Min Act: -0.0000

Data Index: 274194 (C4 (Web Text))

Max Activating Token Index: 320

Text #11

Max Range: 1.4237. Min Range: -1.4237

Max Act: 0.9925. Min Act: -0.0000

Data Index: 429135 (C4 (Web Text))

Max Activating Token Index: 264

Text #12

Max Range: 1.4237. Min Range: -1.4237

Max Act: 0.9777. Min Act: -0.0001

Data Index: 876597 (C4 (Web Text))

Max Activating Token Index: 559

Text #13

Max Range: 1.4237. Min Range: -1.4237

Max Act: 0.9977. Min Act: -0.0000

Data Index: 982078 (C4 (Web Text))

Max Activating Token Index: 119

Text #14

Max Range: 1.4237. Min Range: -1.4237

Max Act: 0.9283. Min Act: -0.0001

Data Index: 288541 (C4 (Web Text))

Max Activating Token Index: 735

Text #15

Max Range: 1.4237. Min Range: -1.4237

Max Act: 0.8908. Min Act: -0.0001

Data Index: 41052 (C4 (Web Text))

Max Activating Token Index: 921

Text #16

Max Range: 1.4237. Min Range: -1.4237

Max Act: 0.9663. Min Act: -0.0001

Data Index: 1115934 (C4 (Web Text))

Max Activating Token Index: 370

Text #17

Max Range: 1.4237. Min Range: -1.4237

Max Act: 0.9577. Min Act: -0.0000

Data Index: 675908 (C4 (Web Text))

Max Activating Token Index: 434

Text #18

Max Range: 1.4237. Min Range: -1.4237

Max Act: 0.9174. Min Act: -0.0001

Data Index: 1042277 (C4 (Web Text))

Max Activating Token Index: 716

Text #19

Max Range: 1.4237. Min Range: -1.4237

Max Act: 0.8638. Min Act: -0.0000

Data Index: 1293331 (C4 (Web Text))

Max Activating Token Index: 503