Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 37 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.2259. Min Act: -0.0000

Data Index: 1661416 (The Pile)

Max Activating Token Index: 36

Text #1

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.1182. Min Act: -0.0000

Data Index: 1971284 (The Pile)

Max Activating Token Index: 122

Text #2

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.0509. Min Act: -0.0000

Data Index: 230701 (The Pile)

Max Activating Token Index: 576

Text #3

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.1508. Min Act: -0.0000

Data Index: 1360964 (The Pile)

Max Activating Token Index: 172

Text #4

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.0527. Min Act: -0.0000

Data Index: 156395 (The Pile)

Max Activating Token Index: 177

Text #5

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.0054. Min Act: -0.0000

Data Index: 791245 (The Pile)

Max Activating Token Index: 561

Text #6

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.0313. Min Act: -0.0000

Data Index: 1042071 (The Pile)

Max Activating Token Index: 634

Text #7

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.0132. Min Act: -0.0000

Data Index: 1126850 (The Pile)

Max Activating Token Index: 468

Text #8

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.0083. Min Act: -0.0000

Data Index: 770503 (The Pile)

Max Activating Token Index: 430

Text #9

Max Range: 1.2259. Min Range: -1.2259

Max Act: 0.9715. Min Act: -0.0000

Data Index: 1869180 (The Pile)

Max Activating Token Index: 88

Text #10

Max Range: 1.2259. Min Range: -1.2259

Max Act: 0.9821. Min Act: -0.0000

Data Index: 457069 (The Pile)

Max Activating Token Index: 54

Text #11

Max Range: 1.2259. Min Range: -1.2259

Max Act: 0.9605. Min Act: -0.0000

Data Index: 62949 (The Pile)

Max Activating Token Index: 789

Text #12

Max Range: 1.2259. Min Range: -1.2259

Max Act: 0.9192. Min Act: -0.0000

Data Index: 48500 (The Pile)

Max Activating Token Index: 596

Text #13

Max Range: 1.2259. Min Range: -1.2259

Max Act: 0.8847. Min Act: -0.0000

Data Index: 1623438 (The Pile)

Max Activating Token Index: 416

Text #14

Max Range: 1.2259. Min Range: -1.2259

Max Act: 0.8740. Min Act: -0.0000

Data Index: 1760372 (The Pile)

Max Activating Token Index: 135

Text #15

Max Range: 1.2259. Min Range: -1.2259

Max Act: 0.9520. Min Act: -0.0000

Data Index: 996502 (The Pile)

Max Activating Token Index: 564

Text #16

Max Range: 1.2259. Min Range: -1.2259

Max Act: 0.9566. Min Act: -0.0000

Data Index: 1810001 (The Pile)

Max Activating Token Index: 136

Text #17

Max Range: 1.2259. Min Range: -1.2259

Max Act: 0.9085. Min Act: -0.0000

Data Index: 1249218 (The Pile)

Max Activating Token Index: 263

Text #18

Max Range: 1.2259. Min Range: -1.2259

Max Act: 0.8831. Min Act: -0.0000

Data Index: 993729 (The Pile)

Max Activating Token Index: 711

Text #19

Max Range: 1.2259. Min Range: -1.2259

Max Act: 0.8291. Min Act: -0.0000

Data Index: 1858236 (The Pile)

Max Activating Token Index: 572