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

Dataset: The Pile

Neuron 2407 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: 0.3160. Min Range: -0.3160

Max Act: 0.3039. Min Act: -0.0000

Data Index: 333248 (The Pile)

Max Activating Token Index: 561

Text #1

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.3085. Min Act: -0.0000

Data Index: 529541 (The Pile)

Max Activating Token Index: 131

Text #2

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.3160. Min Act: -0.0000

Data Index: 1441530 (The Pile)

Max Activating Token Index: 1003

Text #3

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.3035. Min Act: -0.0000

Data Index: 633919 (The Pile)

Max Activating Token Index: 168

Text #4

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2912. Min Act: -0.0000

Data Index: 926362 (The Pile)

Max Activating Token Index: 179

Text #5

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.3088. Min Act: -0.0000

Data Index: 1456420 (The Pile)

Max Activating Token Index: 671

Text #6

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2876. Min Act: -0.0000

Data Index: 166825 (The Pile)

Max Activating Token Index: 242

Text #7

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2845. Min Act: -0.0000

Data Index: 70801 (The Pile)

Max Activating Token Index: 158

Text #8

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2747. Min Act: -0.0000

Data Index: 1462902 (The Pile)

Max Activating Token Index: 15

Text #9

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2740. Min Act: -0.0000

Data Index: 1287908 (The Pile)

Max Activating Token Index: 366

Text #10

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2820. Min Act: -0.0000

Data Index: 531889 (The Pile)

Max Activating Token Index: 132

Text #11

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2816. Min Act: -0.0000

Data Index: 53901 (The Pile)

Max Activating Token Index: 471

Text #12

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2626. Min Act: -0.0000

Data Index: 1143318 (The Pile)

Max Activating Token Index: 415

Text #13

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2793. Min Act: -0.0000

Data Index: 990439 (The Pile)

Max Activating Token Index: 25

Text #14

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2702. Min Act: -0.0000

Data Index: 520150 (The Pile)

Max Activating Token Index: 893

Text #15

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2743. Min Act: -0.0000

Data Index: 1221488 (The Pile)

Max Activating Token Index: 951

Text #16

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2655. Min Act: -0.0000

Data Index: 1070421 (The Pile)

Max Activating Token Index: 453

Text #17

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2747. Min Act: -0.0000

Data Index: 1558186 (The Pile)

Max Activating Token Index: 311

Text #18

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2712. Min Act: -0.0000

Data Index: 666663 (The Pile)

Max Activating Token Index: 914

Text #19

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2469. Min Act: -0.0000

Data Index: 952983 (The Pile)

Max Activating Token Index: 800