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

Dataset: The Pile

Neuron 2552 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: 0.3091. Min Range: -0.3091

Max Act: 0.3091. Min Act: -0.0000

Data Index: 121130 (The Pile)

Max Activating Token Index: 51

Text #1

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.2928. Min Act: -0.0000

Data Index: 1221408 (The Pile)

Max Activating Token Index: 216

Text #2

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.2448. Min Act: -0.0000

Data Index: 52533 (The Pile)

Max Activating Token Index: 267

Text #3

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.2463. Min Act: -0.0000

Data Index: 1380263 (The Pile)

Max Activating Token Index: 1001

Text #4

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.2557. Min Act: -0.0000

Data Index: 167232 (The Pile)

Max Activating Token Index: 741

Text #5

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.2453. Min Act: -0.0000

Data Index: 562366 (The Pile)

Max Activating Token Index: 853

Text #6

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.2329. Min Act: -0.0000

Data Index: 1509984 (The Pile)

Max Activating Token Index: 766

Text #7

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.2442. Min Act: -0.0000

Data Index: 1678927 (The Pile)

Max Activating Token Index: 528

Text #8

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.2380. Min Act: -0.0000

Data Index: 103304 (The Pile)

Max Activating Token Index: 530

Text #9

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.2194. Min Act: -0.0000

Data Index: 1391588 (The Pile)

Max Activating Token Index: 1013

Text #10

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.1972. Min Act: -0.0000

Data Index: 809160 (The Pile)

Max Activating Token Index: 1009

Text #11

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.2084. Min Act: -0.0000

Data Index: 1163755 (The Pile)

Max Activating Token Index: 941

Text #12

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.2142. Min Act: -0.0000

Data Index: 865871 (The Pile)

Max Activating Token Index: 969

Text #13

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.2309. Min Act: -0.0000

Data Index: 376545 (The Pile)

Max Activating Token Index: 874

Text #14

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.2213. Min Act: -0.0000

Data Index: 1795483 (The Pile)

Max Activating Token Index: 552

Text #15

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.2108. Min Act: -0.0000

Data Index: 1193566 (The Pile)

Max Activating Token Index: 273

Text #16

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.2251. Min Act: -0.0000

Data Index: 1099229 (The Pile)

Max Activating Token Index: 153

Text #17

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.2092. Min Act: -0.0000

Data Index: 1735917 (The Pile)

Max Activating Token Index: 95

Text #18

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.2099. Min Act: -0.0000

Data Index: 1891458 (The Pile)

Max Activating Token Index: 591

Text #19

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.2126. Min Act: -0.0000

Data Index: 257448 (The Pile)

Max Activating Token Index: 671