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

Dataset: The Pile

Neuron 1122 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: 0.4163. Min Range: -0.4163

Max Act: 0.4163. Min Act: -0.0000

Data Index: 26486 (The Pile)

Max Activating Token Index: 54

Text #1

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.4124. Min Act: -0.0000

Data Index: 1150405 (The Pile)

Max Activating Token Index: 354

Text #2

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.3634. Min Act: -0.0000

Data Index: 951380 (The Pile)

Max Activating Token Index: 836

Text #3

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.3487. Min Act: -0.0000

Data Index: 1519582 (The Pile)

Max Activating Token Index: 1007

Text #4

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.3588. Min Act: -0.0000

Data Index: 1871474 (The Pile)

Max Activating Token Index: 621

Text #5

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.3655. Min Act: -0.0000

Data Index: 1084690 (The Pile)

Max Activating Token Index: 358

Text #6

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.2961. Min Act: -0.0000

Data Index: 302714 (The Pile)

Max Activating Token Index: 831

Text #7

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.3346. Min Act: -0.0000

Data Index: 228391 (The Pile)

Max Activating Token Index: 598

Text #8

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.3329. Min Act: -0.0000

Data Index: 130377 (The Pile)

Max Activating Token Index: 645

Text #9

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.3281. Min Act: -0.0000

Data Index: 48679 (The Pile)

Max Activating Token Index: 949

Text #10

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.3395. Min Act: -0.0000

Data Index: 307332 (The Pile)

Max Activating Token Index: 107

Text #11

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.2969. Min Act: -0.0000

Data Index: 969250 (The Pile)

Max Activating Token Index: 35

Text #12

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.3167. Min Act: -0.0000

Data Index: 211177 (The Pile)

Max Activating Token Index: 642

Text #13

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.2479. Min Act: -0.0000

Data Index: 1186095 (The Pile)

Max Activating Token Index: 739

Text #14

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.2833. Min Act: -0.0000

Data Index: 1130819 (The Pile)

Max Activating Token Index: 663

Text #15

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.3028. Min Act: -0.0000

Data Index: 1811135 (The Pile)

Max Activating Token Index: 385

Text #16

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.2607. Min Act: -0.0000

Data Index: 206374 (The Pile)

Max Activating Token Index: 930

Text #17

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.3002. Min Act: -0.0000

Data Index: 482985 (The Pile)

Max Activating Token Index: 875

Text #18

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.3176. Min Act: -0.0000

Data Index: 1013665 (The Pile)

Max Activating Token Index: 325

Text #19

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.2956. Min Act: -0.0000

Data Index: 47003 (The Pile)

Max Activating Token Index: 479