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

Dataset: The Pile

Neuron 4796 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4168. Min Range: -1.4168

Max Act: 1.4168. Min Act: -0.0000

Data Index: 47166 (The Pile)

Max Activating Token Index: 461

Text #1

Max Range: 1.4168. Min Range: -1.4168

Max Act: 1.2859. Min Act: 0.0000

Data Index: 535610 (The Pile)

Max Activating Token Index: 664

Text #2

Max Range: 1.4168. Min Range: -1.4168

Max Act: 1.1432. Min Act: -0.0000

Data Index: 1581634 (The Pile)

Max Activating Token Index: 772

Text #3

Max Range: 1.4168. Min Range: -1.4168

Max Act: 1.1058. Min Act: -0.0000

Data Index: 1122975 (The Pile)

Max Activating Token Index: 230

Text #4

Max Range: 1.4168. Min Range: -1.4168

Max Act: 1.1005. Min Act: -0.0000

Data Index: 1243249 (The Pile)

Max Activating Token Index: 469

Text #5

Max Range: 1.4168. Min Range: -1.4168

Max Act: 1.1774. Min Act: -0.0000

Data Index: 1147671 (The Pile)

Max Activating Token Index: 222

Text #6

Max Range: 1.4168. Min Range: -1.4168

Max Act: 1.1375. Min Act: -0.0000

Data Index: 615049 (The Pile)

Max Activating Token Index: 451

Text #7

Max Range: 1.4168. Min Range: -1.4168

Max Act: 1.0385. Min Act: -0.0000

Data Index: 1064021 (The Pile)

Max Activating Token Index: 57

Text #8

Max Range: 1.4168. Min Range: -1.4168

Max Act: 1.0640. Min Act: -0.0000

Data Index: 303885 (The Pile)

Max Activating Token Index: 286

Text #9

Max Range: 1.4168. Min Range: -1.4168

Max Act: 1.0254. Min Act: -0.0000

Data Index: 577917 (The Pile)

Max Activating Token Index: 741

Text #10

Max Range: 1.4168. Min Range: -1.4168

Max Act: 0.9127. Min Act: -0.0000

Data Index: 436974 (The Pile)

Max Activating Token Index: 107

Text #11

Max Range: 1.4168. Min Range: -1.4168

Max Act: 1.0188. Min Act: -0.0000

Data Index: 469128 (The Pile)

Max Activating Token Index: 74

Text #12

Max Range: 1.4168. Min Range: -1.4168

Max Act: 0.8868. Min Act: -0.0000

Data Index: 1933830 (The Pile)

Max Activating Token Index: 791

Text #13

Max Range: 1.4168. Min Range: -1.4168

Max Act: 0.9700. Min Act: -0.0000

Data Index: 762631 (The Pile)

Max Activating Token Index: 26

Text #14

Max Range: 1.4168. Min Range: -1.4168

Max Act: 0.9432. Min Act: -0.0000

Data Index: 208362 (The Pile)

Max Activating Token Index: 224

Text #15

Max Range: 1.4168. Min Range: -1.4168

Max Act: 0.9628. Min Act: -0.0000

Data Index: 83316 (The Pile)

Max Activating Token Index: 592

Text #16

Max Range: 1.4168. Min Range: -1.4168

Max Act: 0.9313. Min Act: -0.0000

Data Index: 423377 (The Pile)

Max Activating Token Index: 973

Text #17

Max Range: 1.4168. Min Range: -1.4168

Max Act: 0.9336. Min Act: -0.0000

Data Index: 1264366 (The Pile)

Max Activating Token Index: 276

Text #18

Max Range: 1.4168. Min Range: -1.4168

Max Act: 0.9914. Min Act: -0.0000

Data Index: 1684578 (The Pile)

Max Activating Token Index: 212

Text #19

Max Range: 1.4168. Min Range: -1.4168

Max Act: 0.8983. Min Act: -0.0000

Data Index: 1190452 (The Pile)

Max Activating Token Index: 418