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

Dataset: The Pile

Neuron 1483 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: 0.2939. Min Range: -0.2939

Max Act: 0.2746. Min Act: -0.0000

Data Index: 278188 (The Pile)

Max Activating Token Index: 565

Text #1

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2939. Min Act: -0.0000

Data Index: 368036 (The Pile)

Max Activating Token Index: 144

Text #2

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2682. Min Act: -0.0000

Data Index: 776494 (The Pile)

Max Activating Token Index: 505

Text #3

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2664. Min Act: -0.0000

Data Index: 1389044 (The Pile)

Max Activating Token Index: 1014

Text #4

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2501. Min Act: -0.0000

Data Index: 994541 (The Pile)

Max Activating Token Index: 319

Text #5

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2391. Min Act: -0.0000

Data Index: 736605 (The Pile)

Max Activating Token Index: 65

Text #6

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2397. Min Act: -0.0000

Data Index: 1333314 (The Pile)

Max Activating Token Index: 111

Text #7

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2169. Min Act: -0.0000

Data Index: 514921 (The Pile)

Max Activating Token Index: 139

Text #8

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2295. Min Act: -0.0000

Data Index: 814436 (The Pile)

Max Activating Token Index: 165

Text #9

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2314. Min Act: -0.0000

Data Index: 1360907 (The Pile)

Max Activating Token Index: 525

Text #10

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2290. Min Act: -0.0000

Data Index: 1124950 (The Pile)

Max Activating Token Index: 731

Text #11

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2259. Min Act: -0.0000

Data Index: 515440 (The Pile)

Max Activating Token Index: 663

Text #12

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2200. Min Act: -0.0000

Data Index: 1123998 (The Pile)

Max Activating Token Index: 635

Text #13

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2154. Min Act: -0.0000

Data Index: 37532 (The Pile)

Max Activating Token Index: 6

Text #14

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2126. Min Act: -0.0000

Data Index: 1961937 (The Pile)

Max Activating Token Index: 908

Text #15

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2011. Min Act: -0.0000

Data Index: 1749230 (The Pile)

Max Activating Token Index: 270

Text #16

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2075. Min Act: -0.0000

Data Index: 1099675 (The Pile)

Max Activating Token Index: 866

Text #17

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2084. Min Act: -0.0000

Data Index: 10917 (The Pile)

Max Activating Token Index: 88

Text #18

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.1980. Min Act: -0.0000

Data Index: 1821796 (The Pile)

Max Activating Token Index: 942

Text #19

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.1897. Min Act: -0.0000

Data Index: 1195335 (The Pile)

Max Activating Token Index: 849