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

Dataset: The Pile

Neuron 1121 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.3474. Min Act: -0.0000

Data Index: 497280 (The Pile)

Max Activating Token Index: 865

Text #1

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.3124. Min Act: -0.0000

Data Index: 376889 (The Pile)

Max Activating Token Index: 537

Text #2

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2727. Min Act: -0.0000

Data Index: 563694 (The Pile)

Max Activating Token Index: 218

Text #3

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2800. Min Act: -0.0000

Data Index: 213240 (The Pile)

Max Activating Token Index: 846

Text #4

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2589. Min Act: -0.0000

Data Index: 1504807 (The Pile)

Max Activating Token Index: 600

Text #5

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2649. Min Act: -0.0000

Data Index: 1894171 (The Pile)

Max Activating Token Index: 161

Text #6

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2438. Min Act: -0.0000

Data Index: 710764 (The Pile)

Max Activating Token Index: 314

Text #7

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2497. Min Act: -0.0000

Data Index: 244850 (The Pile)

Max Activating Token Index: 646

Text #8

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2536. Min Act: -0.0000

Data Index: 1350034 (The Pile)

Max Activating Token Index: 851

Text #9

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2488. Min Act: -0.0000

Data Index: 1997925 (The Pile)

Max Activating Token Index: 337

Text #10

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2371. Min Act: -0.0000

Data Index: 741923 (The Pile)

Max Activating Token Index: 403

Text #11

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2319. Min Act: -0.0000

Data Index: 1522757 (The Pile)

Max Activating Token Index: 356

Text #12

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2383. Min Act: -0.0000

Data Index: 813876 (The Pile)

Max Activating Token Index: 869

Text #13

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2210. Min Act: -0.0000

Data Index: 236957 (The Pile)

Max Activating Token Index: 191

Text #14

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2159. Min Act: -0.0000

Data Index: 677596 (The Pile)

Max Activating Token Index: 965

Text #15

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2227. Min Act: -0.0000

Data Index: 117466 (The Pile)

Max Activating Token Index: 344

Text #16

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2382. Min Act: -0.0000

Data Index: 125488 (The Pile)

Max Activating Token Index: 237

Text #17

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2297. Min Act: -0.0000

Data Index: 192451 (The Pile)

Max Activating Token Index: 596

Text #18

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2179. Min Act: -0.0000

Data Index: 150036 (The Pile)

Max Activating Token Index: 419

Text #19

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2079. Min Act: -0.0000

Data Index: 1929977 (The Pile)

Max Activating Token Index: 169