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

Dataset: The Pile

Neuron 2811 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: 0.4215. Min Range: -0.4215

Max Act: 0.4215. Min Act: -0.0000

Data Index: 405065 (The Pile)

Max Activating Token Index: 40

Text #1

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.3734. Min Act: -0.0000

Data Index: 110384 (The Pile)

Max Activating Token Index: 20

Text #2

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.3328. Min Act: -0.0000

Data Index: 1245313 (The Pile)

Max Activating Token Index: 146

Text #3

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.3576. Min Act: -0.0000

Data Index: 980671 (The Pile)

Max Activating Token Index: 660

Text #4

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.2944. Min Act: -0.0000

Data Index: 1583076 (The Pile)

Max Activating Token Index: 301

Text #5

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.3239. Min Act: -0.0000

Data Index: 304266 (The Pile)

Max Activating Token Index: 883

Text #6

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.3198. Min Act: -0.0000

Data Index: 1650231 (The Pile)

Max Activating Token Index: 829

Text #7

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.2786. Min Act: -0.0000

Data Index: 1135610 (The Pile)

Max Activating Token Index: 955

Text #8

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.2791. Min Act: -0.0000

Data Index: 264349 (The Pile)

Max Activating Token Index: 625

Text #9

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.3355. Min Act: -0.0000

Data Index: 363045 (The Pile)

Max Activating Token Index: 621

Text #10

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.2806. Min Act: -0.0000

Data Index: 1301488 (The Pile)

Max Activating Token Index: 571

Text #11

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.2202. Min Act: -0.0000

Data Index: 1112000 (The Pile)

Max Activating Token Index: 248

Text #12

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.2646. Min Act: -0.0000

Data Index: 1774278 (The Pile)

Max Activating Token Index: 989

Text #13

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.2347. Min Act: -0.0000

Data Index: 1176954 (The Pile)

Max Activating Token Index: 454

Text #14

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.2249. Min Act: -0.0000

Data Index: 165878 (The Pile)

Max Activating Token Index: 759

Text #15

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.2236. Min Act: -0.0000

Data Index: 1291363 (The Pile)

Max Activating Token Index: 562

Text #16

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.2228. Min Act: -0.0000

Data Index: 1870128 (The Pile)

Max Activating Token Index: 313

Text #17

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.2345. Min Act: -0.0000

Data Index: 400540 (The Pile)

Max Activating Token Index: 896

Text #18

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.2314. Min Act: -0.0000

Data Index: 702512 (The Pile)

Max Activating Token Index: 941

Text #19

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.2133. Min Act: -0.0000

Data Index: 1130715 (The Pile)

Max Activating Token Index: 834