Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 917 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2485. Min Act: -0.0000

Data Index: 934322 (The Pile)

Max Activating Token Index: 215

Text #1

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2560. Min Act: -0.0000

Data Index: 910724 (The Pile)

Max Activating Token Index: 145

Text #2

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2554. Min Act: -0.0000

Data Index: 699054 (The Pile)

Max Activating Token Index: 797

Text #3

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2441. Min Act: -0.0000

Data Index: 1948340 (The Pile)

Max Activating Token Index: 616

Text #4

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2302. Min Act: -0.0000

Data Index: 1019079 (The Pile)

Max Activating Token Index: 491

Text #5

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2229. Min Act: -0.0000

Data Index: 404063 (The Pile)

Max Activating Token Index: 312

Text #6

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2349. Min Act: -0.0000

Data Index: 458522 (The Pile)

Max Activating Token Index: 708

Text #7

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2266. Min Act: -0.0000

Data Index: 1851478 (The Pile)

Max Activating Token Index: 304

Text #8

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2180. Min Act: -0.0000

Data Index: 57767 (The Pile)

Max Activating Token Index: 106

Text #9

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2179. Min Act: -0.0000

Data Index: 1389126 (The Pile)

Max Activating Token Index: 432

Text #10

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2231. Min Act: -0.0000

Data Index: 791643 (The Pile)

Max Activating Token Index: 421

Text #11

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2249. Min Act: -0.0000

Data Index: 370902 (The Pile)

Max Activating Token Index: 589

Text #12

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2174. Min Act: -0.0000

Data Index: 937332 (The Pile)

Max Activating Token Index: 927

Text #13

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2180. Min Act: -0.0000

Data Index: 1094698 (The Pile)

Max Activating Token Index: 204

Text #14

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.1877. Min Act: -0.0000

Data Index: 974387 (The Pile)

Max Activating Token Index: 514

Text #15

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2066. Min Act: -0.0000

Data Index: 1408290 (The Pile)

Max Activating Token Index: 473

Text #16

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2023. Min Act: -0.0000

Data Index: 1945265 (The Pile)

Max Activating Token Index: 159

Text #17

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2066. Min Act: -0.0000

Data Index: 1277314 (The Pile)

Max Activating Token Index: 935

Text #18

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.1819. Min Act: -0.0000

Data Index: 1422524 (The Pile)

Max Activating Token Index: 197

Text #19

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2009. Min Act: -0.0000

Data Index: 652531 (The Pile)

Max Activating Token Index: 35