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

Dataset: The Pile

Neuron 1845 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: 3.1116. Min Range: -3.1116

Max Act: 3.1116. Min Act: -0.0000

Data Index: 1765694 (The Pile)

Max Activating Token Index: 976

Text #1

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.9068. Min Act: -0.0000

Data Index: 506303 (The Pile)

Max Activating Token Index: 683

Text #2

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.7278. Min Act: -0.0000

Data Index: 362599 (The Pile)

Max Activating Token Index: 367

Text #3

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.2633. Min Act: -0.0000

Data Index: 1901820 (The Pile)

Max Activating Token Index: 173

Text #4

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.2601. Min Act: -0.0000

Data Index: 1181889 (The Pile)

Max Activating Token Index: 1007

Text #5

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.1900. Min Act: -0.0000

Data Index: 1392365 (The Pile)

Max Activating Token Index: 905

Text #6

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.4034. Min Act: -0.0000

Data Index: 165778 (The Pile)

Max Activating Token Index: 839

Text #7

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.0559. Min Act: -0.0000

Data Index: 1867782 (The Pile)

Max Activating Token Index: 137

Text #8

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.2206. Min Act: -0.0000

Data Index: 296292 (The Pile)

Max Activating Token Index: 223

Text #9

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.0677. Min Act: -0.0000

Data Index: 761967 (The Pile)

Max Activating Token Index: 136

Text #10

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.1937. Min Act: -0.0000

Data Index: 472345 (The Pile)

Max Activating Token Index: 497

Text #11

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.0286. Min Act: -0.0000

Data Index: 183652 (The Pile)

Max Activating Token Index: 592

Text #12

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.1106. Min Act: -0.0000

Data Index: 1700980 (The Pile)

Max Activating Token Index: 401

Text #13

Max Range: 3.1116. Min Range: -3.1116

Max Act: 1.9731. Min Act: -0.0000

Data Index: 1457752 (The Pile)

Max Activating Token Index: 268

Text #14

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.1871. Min Act: -0.0000

Data Index: 1296207 (The Pile)

Max Activating Token Index: 376

Text #15

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.0771. Min Act: -0.0000

Data Index: 1211720 (The Pile)

Max Activating Token Index: 511

Text #16

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.0679. Min Act: -0.0000

Data Index: 1064441 (The Pile)

Max Activating Token Index: 643

Text #17

Max Range: 3.1116. Min Range: -3.1116

Max Act: 1.9426. Min Act: -0.0000

Data Index: 1212144 (The Pile)

Max Activating Token Index: 333

Text #18

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.0318. Min Act: -0.0000

Data Index: 567021 (The Pile)

Max Activating Token Index: 404

Text #19

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.0190. Min Act: -0.0000

Data Index: 1041189 (The Pile)

Max Activating Token Index: 484