Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 537 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4355. Min Range: -0.4355

Max Act: 0.4317. Min Act: -0.0001

Data Index: 596182 (C4 (Web Text))

Max Activating Token Index: 7

Text #1

Max Range: 0.4355. Min Range: -0.4355

Max Act: 0.4355. Min Act: -0.0001

Data Index: 481838 (C4 (Web Text))

Max Activating Token Index: 663

Text #2

Max Range: 0.4355. Min Range: -0.4355

Max Act: 0.4231. Min Act: -0.0001

Data Index: 742417 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 0.4355. Min Range: -0.4355

Max Act: 0.4165. Min Act: -0.0001

Data Index: 72800 (C4 (Web Text))

Max Activating Token Index: 896

Text #4

Max Range: 0.4355. Min Range: -0.4355

Max Act: 0.3854. Min Act: -0.0001

Data Index: 343790 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 0.4355. Min Range: -0.4355

Max Act: 0.4179. Min Act: -0.0001

Data Index: 105502 (C4 (Web Text))

Max Activating Token Index: 521

Text #6

Max Range: 0.4355. Min Range: -0.4355

Max Act: 0.3945. Min Act: -0.0001

Data Index: 1198388 (C4 (Web Text))

Max Activating Token Index: 151

Text #7

Max Range: 0.4355. Min Range: -0.4355

Max Act: 0.3791. Min Act: -0.0001

Data Index: 981095 (C4 (Web Text))

Max Activating Token Index: 235

Text #8

Max Range: 0.4355. Min Range: -0.4355

Max Act: 0.3753. Min Act: -0.0001

Data Index: 356556 (C4 (Web Text))

Max Activating Token Index: 478

Text #9

Max Range: 0.4355. Min Range: -0.4355

Max Act: 0.3646. Min Act: -0.0001

Data Index: 1342001 (C4 (Web Text))

Max Activating Token Index: 91

Text #10

Max Range: 0.4355. Min Range: -0.4355

Max Act: 0.3615. Min Act: -0.0001

Data Index: 1282678 (C4 (Web Text))

Max Activating Token Index: 136

Text #11

Max Range: 0.4355. Min Range: -0.4355

Max Act: 0.3681. Min Act: -0.0001

Data Index: 272480 (C4 (Web Text))

Max Activating Token Index: 306

Text #12

Max Range: 0.4355. Min Range: -0.4355

Max Act: 0.3362. Min Act: -0.0001

Data Index: 261061 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 0.4355. Min Range: -0.4355

Max Act: 0.3446. Min Act: -0.0001

Data Index: 841597 (C4 (Web Text))

Max Activating Token Index: 118

Text #14

Max Range: 0.4355. Min Range: -0.4355

Max Act: 0.3225. Min Act: -0.0001

Data Index: 1344439 (C4 (Web Text))

Max Activating Token Index: 114

Text #15

Max Range: 0.4355. Min Range: -0.4355

Max Act: 0.3257. Min Act: -0.0001

Data Index: 201001 (C4 (Web Text))

Max Activating Token Index: 189

Text #16

Max Range: 0.4355. Min Range: -0.4355

Max Act: 0.3248. Min Act: -0.0001

Data Index: 793133 (C4 (Web Text))

Max Activating Token Index: 706

Text #17

Max Range: 0.4355. Min Range: -0.4355

Max Act: 0.3264. Min Act: -0.0001

Data Index: 33637 (C4 (Web Text))

Max Activating Token Index: 257

Text #18

Max Range: 0.4355. Min Range: -0.4355

Max Act: 0.3459. Min Act: -0.0001

Data Index: 367834 (C4 (Web Text))

Max Activating Token Index: 255

Text #19

Max Range: 0.4355. Min Range: -0.4355

Max Act: 0.3270. Min Act: -0.0001

Data Index: 91726 (C4 (Web Text))

Max Activating Token Index: 199