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

Dataset: The Pile

Neuron 1771 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9359. Min Range: -0.9359

Max Act: 0.9283. Min Act: -0.0000

Data Index: 1871365 (The Pile)

Max Activating Token Index: 753

Text #1

Max Range: 0.9359. Min Range: -0.9359

Max Act: 0.9359. Min Act: -0.0000

Data Index: 1711557 (The Pile)

Max Activating Token Index: 30

Text #2

Max Range: 0.9359. Min Range: -0.9359

Max Act: 0.8699. Min Act: -0.0000

Data Index: 1215568 (The Pile)

Max Activating Token Index: 859

Text #3

Max Range: 0.9359. Min Range: -0.9359

Max Act: 0.8632. Min Act: -0.0000

Data Index: 1022256 (The Pile)

Max Activating Token Index: 965

Text #4

Max Range: 0.9359. Min Range: -0.9359

Max Act: 0.8193. Min Act: -0.0000

Data Index: 1699490 (The Pile)

Max Activating Token Index: 496

Text #5

Max Range: 0.9359. Min Range: -0.9359

Max Act: 0.8168. Min Act: -0.0000

Data Index: 600100 (The Pile)

Max Activating Token Index: 62

Text #6

Max Range: 0.9359. Min Range: -0.9359

Max Act: 0.7894. Min Act: -0.0000

Data Index: 672882 (The Pile)

Max Activating Token Index: 309

Text #7

Max Range: 0.9359. Min Range: -0.9359

Max Act: 0.8119. Min Act: -0.0000

Data Index: 871256 (The Pile)

Max Activating Token Index: 192

Text #8

Max Range: 0.9359. Min Range: -0.9359

Max Act: 0.8553. Min Act: -0.0000

Data Index: 651916 (The Pile)

Max Activating Token Index: 303

Text #9

Max Range: 0.9359. Min Range: -0.9359

Max Act: 0.8118. Min Act: -0.0000

Data Index: 1932290 (The Pile)

Max Activating Token Index: 912

Text #10

Max Range: 0.9359. Min Range: -0.9359

Max Act: 0.7587. Min Act: -0.0000

Data Index: 398374 (The Pile)

Max Activating Token Index: 996

Text #11

Max Range: 0.9359. Min Range: -0.9359

Max Act: 0.7644. Min Act: -0.0000

Data Index: 309107 (The Pile)

Max Activating Token Index: 341

Text #12

Max Range: 0.9359. Min Range: -0.9359

Max Act: 0.8292. Min Act: -0.0000

Data Index: 1612871 (The Pile)

Max Activating Token Index: 932

Text #13

Max Range: 0.9359. Min Range: -0.9359

Max Act: 0.7513. Min Act: -0.0000

Data Index: 1127128 (The Pile)

Max Activating Token Index: 955

Text #14

Max Range: 0.9359. Min Range: -0.9359

Max Act: 0.8001. Min Act: -0.0000

Data Index: 1332205 (The Pile)

Max Activating Token Index: 305

Text #15

Max Range: 0.9359. Min Range: -0.9359

Max Act: 0.7957. Min Act: -0.0000

Data Index: 1364458 (The Pile)

Max Activating Token Index: 172

Text #16

Max Range: 0.9359. Min Range: -0.9359

Max Act: 0.7955. Min Act: -0.0000

Data Index: 372705 (The Pile)

Max Activating Token Index: 967

Text #17

Max Range: 0.9359. Min Range: -0.9359

Max Act: 0.8193. Min Act: -0.0000

Data Index: 535283 (The Pile)

Max Activating Token Index: 867

Text #18

Max Range: 0.9359. Min Range: -0.9359

Max Act: 0.7779. Min Act: -0.0000

Data Index: 1593023 (The Pile)

Max Activating Token Index: 856

Text #19

Max Range: 0.9359. Min Range: -0.9359

Max Act: 0.8015. Min Act: -0.0000

Data Index: 493911 (The Pile)

Max Activating Token Index: 356