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

Dataset: The Pile

Neuron 3857 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: 1.5922. Min Range: -1.5922

Max Act: 1.5313. Min Act: -0.0000

Data Index: 966588 (The Pile)

Max Activating Token Index: 869

Text #1

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.5922. Min Act: -0.0000

Data Index: 39820 (The Pile)

Max Activating Token Index: 127

Text #2

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.4652. Min Act: -0.0000

Data Index: 1363931 (The Pile)

Max Activating Token Index: 578

Text #3

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.4146. Min Act: -0.0000

Data Index: 783436 (The Pile)

Max Activating Token Index: 402

Text #4

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.3208. Min Act: -0.0000

Data Index: 678709 (The Pile)

Max Activating Token Index: 380

Text #5

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.3297. Min Act: -0.0000

Data Index: 1385702 (The Pile)

Max Activating Token Index: 45

Text #6

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.2792. Min Act: -0.0000

Data Index: 1484147 (The Pile)

Max Activating Token Index: 486

Text #7

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.2079. Min Act: -0.0000

Data Index: 689045 (The Pile)

Max Activating Token Index: 833

Text #8

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.2685. Min Act: -0.0000

Data Index: 1158267 (The Pile)

Max Activating Token Index: 216

Text #9

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.3012. Min Act: -0.0000

Data Index: 1830214 (The Pile)

Max Activating Token Index: 410

Text #10

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.2225. Min Act: -0.0000

Data Index: 863441 (The Pile)

Max Activating Token Index: 39

Text #11

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.1849. Min Act: -0.0000

Data Index: 440320 (The Pile)

Max Activating Token Index: 621

Text #12

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.2159. Min Act: -0.0000

Data Index: 533606 (The Pile)

Max Activating Token Index: 302

Text #13

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.2163. Min Act: -0.0000

Data Index: 1303366 (The Pile)

Max Activating Token Index: 518

Text #14

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.2282. Min Act: -0.0000

Data Index: 443587 (The Pile)

Max Activating Token Index: 835

Text #15

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.2327. Min Act: -0.0000

Data Index: 668033 (The Pile)

Max Activating Token Index: 36

Text #16

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.1990. Min Act: -0.0000

Data Index: 1397343 (The Pile)

Max Activating Token Index: 123

Text #17

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.2189. Min Act: -0.0000

Data Index: 1346757 (The Pile)

Max Activating Token Index: 898

Text #18

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.1513. Min Act: -0.0000

Data Index: 1256010 (The Pile)

Max Activating Token Index: 61

Text #19

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.2089. Min Act: -0.0000

Data Index: 1213916 (The Pile)

Max Activating Token Index: 907