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

Dataset: The Pile

Neuron 4091 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.7297. Min Range: -7.7297

Max Act: 7.7297. Min Act: -0.0000

Data Index: 102165 (The Pile)

Max Activating Token Index: 958

Text #1

Max Range: 7.7297. Min Range: -7.7297

Max Act: 3.2387. Min Act: -0.0000

Data Index: 1779347 (The Pile)

Max Activating Token Index: 986

Text #2

Max Range: 7.7297. Min Range: -7.7297

Max Act: 4.1229. Min Act: -0.0000

Data Index: 1290846 (The Pile)

Max Activating Token Index: 75

Text #3

Max Range: 7.7297. Min Range: -7.7297

Max Act: 0.0601. Min Act: -0.0000

Data Index: 324803 (The Pile)

Max Activating Token Index: 1014

Text #4

Max Range: 7.7297. Min Range: -7.7297

Max Act: 0.0924. Min Act: -0.0000

Data Index: 1558925 (The Pile)

Max Activating Token Index: 403

Text #5

Max Range: 7.7297. Min Range: -7.7297

Max Act: 1.5586. Min Act: -0.0000

Data Index: 827512 (The Pile)

Max Activating Token Index: 796

Text #6

Max Range: 7.7297. Min Range: -7.7297

Max Act: 0.1026. Min Act: -0.0000

Data Index: 526931 (The Pile)

Max Activating Token Index: 638

Text #7

Max Range: 7.7297. Min Range: -7.7297

Max Act: 1.8152. Min Act: -0.0000

Data Index: 1242424 (The Pile)

Max Activating Token Index: 355

Text #8

Max Range: 7.7297. Min Range: -7.7297

Max Act: 0.5873. Min Act: -0.0000

Data Index: 1737774 (The Pile)

Max Activating Token Index: 978

Text #9

Max Range: 7.7297. Min Range: -7.7297

Max Act: 1.1373. Min Act: -0.0000

Data Index: 1563261 (The Pile)

Max Activating Token Index: 269

Text #10

Max Range: 7.7297. Min Range: -7.7297

Max Act: 0.7877. Min Act: -0.0000

Data Index: 1870219 (The Pile)

Max Activating Token Index: 893

Text #11

Max Range: 7.7297. Min Range: -7.7297

Max Act: 0.4469. Min Act: -0.0000

Data Index: 931121 (The Pile)

Max Activating Token Index: 790

Text #12

Max Range: 7.7297. Min Range: -7.7297

Max Act: 0.4082. Min Act: -0.0000

Data Index: 590460 (The Pile)

Max Activating Token Index: 720

Text #13

Max Range: 7.7297. Min Range: -7.7297

Max Act: 0.3485. Min Act: -0.0000

Data Index: 1118145 (The Pile)

Max Activating Token Index: 149

Text #14

Max Range: 7.7297. Min Range: -7.7297

Max Act: 0.3282. Min Act: -0.0000

Data Index: 1077637 (The Pile)

Max Activating Token Index: 1002

Text #15

Max Range: 7.7297. Min Range: -7.7297

Max Act: 0.3087. Min Act: -0.0000

Data Index: 1028478 (The Pile)

Max Activating Token Index: 543

Text #16

Max Range: 7.7297. Min Range: -7.7297

Max Act: 0.3056. Min Act: -0.0000

Data Index: 1050684 (The Pile)

Max Activating Token Index: 454

Text #17

Max Range: 7.7297. Min Range: -7.7297

Max Act: 0.3279. Min Act: -0.0000

Data Index: 1197419 (The Pile)

Max Activating Token Index: 682

Text #18

Max Range: 7.7297. Min Range: -7.7297

Max Act: 0.2979. Min Act: -0.0000

Data Index: 1214451 (The Pile)

Max Activating Token Index: 87

Text #19

Max Range: 7.7297. Min Range: -7.7297

Max Act: 0.3403. Min Act: -0.0000

Data Index: 348036 (The Pile)

Max Activating Token Index: 616