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

Dataset: The Pile

Neuron 4533 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: 0.6085. Min Range: -0.6085

Max Act: 0.6085. Min Act: -0.0000

Data Index: 439462 (The Pile)

Max Activating Token Index: 514

Text #1

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.5058. Min Act: -0.0000

Data Index: 125285 (The Pile)

Max Activating Token Index: 492

Text #2

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.5647. Min Act: -0.0000

Data Index: 1510974 (The Pile)

Max Activating Token Index: 874

Text #3

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.5192. Min Act: -0.0000

Data Index: 182111 (The Pile)

Max Activating Token Index: 818

Text #4

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.4875. Min Act: -0.0000

Data Index: 1540763 (The Pile)

Max Activating Token Index: 94

Text #5

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.5315. Min Act: -0.0000

Data Index: 1122828 (The Pile)

Max Activating Token Index: 955

Text #6

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.4144. Min Act: -0.0000

Data Index: 1098339 (The Pile)

Max Activating Token Index: 869

Text #7

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.4538. Min Act: -0.0000

Data Index: 1395217 (The Pile)

Max Activating Token Index: 235

Text #8

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.4940. Min Act: -0.0000

Data Index: 824879 (The Pile)

Max Activating Token Index: 668

Text #9

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.4291. Min Act: -0.0000

Data Index: 438055 (The Pile)

Max Activating Token Index: 807

Text #10

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.4337. Min Act: -0.0000

Data Index: 993179 (The Pile)

Max Activating Token Index: 204

Text #11

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.4006. Min Act: -0.0000

Data Index: 929995 (The Pile)

Max Activating Token Index: 237

Text #12

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.3868. Min Act: -0.0000

Data Index: 1411220 (The Pile)

Max Activating Token Index: 946

Text #13

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.3965. Min Act: -0.0000

Data Index: 1044574 (The Pile)

Max Activating Token Index: 593

Text #14

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.3812. Min Act: -0.0000

Data Index: 1912026 (The Pile)

Max Activating Token Index: 132

Text #15

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.4113. Min Act: -0.0000

Data Index: 129695 (The Pile)

Max Activating Token Index: 977

Text #16

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.3835. Min Act: -0.0000

Data Index: 1045222 (The Pile)

Max Activating Token Index: 667

Text #17

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.3572. Min Act: -0.0000

Data Index: 506749 (The Pile)

Max Activating Token Index: 474

Text #18

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.3406. Min Act: -0.0000

Data Index: 1183476 (The Pile)

Max Activating Token Index: 883

Text #19

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.3923. Min Act: -0.0000

Data Index: 400361 (The Pile)

Max Activating Token Index: 870