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

Dataset: The Pile

Neuron 4678 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1929. Min Range: -1.1929

Max Act: 1.1595. Min Act: -0.0000

Data Index: 1259538 (The Pile)

Max Activating Token Index: 237

Text #1

Max Range: 1.1929. Min Range: -1.1929

Max Act: 1.1368. Min Act: -0.0000

Data Index: 462053 (The Pile)

Max Activating Token Index: 571

Text #2

Max Range: 1.1929. Min Range: -1.1929

Max Act: 1.0386. Min Act: -0.0000

Data Index: 105133 (The Pile)

Max Activating Token Index: 1020

Text #3

Max Range: 1.1929. Min Range: -1.1929

Max Act: 1.1929. Min Act: -0.0000

Data Index: 419681 (The Pile)

Max Activating Token Index: 827

Text #4

Max Range: 1.1929. Min Range: -1.1929

Max Act: 0.9032. Min Act: -0.0000

Data Index: 594503 (The Pile)

Max Activating Token Index: 792

Text #5

Max Range: 1.1929. Min Range: -1.1929

Max Act: 1.0490. Min Act: -0.0000

Data Index: 242375 (The Pile)

Max Activating Token Index: 477

Text #6

Max Range: 1.1929. Min Range: -1.1929

Max Act: 1.0642. Min Act: -0.0000

Data Index: 668238 (The Pile)

Max Activating Token Index: 158

Text #7

Max Range: 1.1929. Min Range: -1.1929

Max Act: 0.9629. Min Act: -0.0000

Data Index: 999518 (The Pile)

Max Activating Token Index: 285

Text #8

Max Range: 1.1929. Min Range: -1.1929

Max Act: 0.9865. Min Act: -0.0000

Data Index: 323875 (The Pile)

Max Activating Token Index: 622

Text #9

Max Range: 1.1929. Min Range: -1.1929

Max Act: 0.8271. Min Act: -0.0000

Data Index: 853966 (The Pile)

Max Activating Token Index: 638

Text #10

Max Range: 1.1929. Min Range: -1.1929

Max Act: 0.9068. Min Act: -0.0000

Data Index: 5663 (The Pile)

Max Activating Token Index: 579

Text #11

Max Range: 1.1929. Min Range: -1.1929

Max Act: 0.8650. Min Act: -0.0000

Data Index: 662244 (The Pile)

Max Activating Token Index: 760

Text #12

Max Range: 1.1929. Min Range: -1.1929

Max Act: 0.8774. Min Act: -0.0000

Data Index: 1873415 (The Pile)

Max Activating Token Index: 340

Text #13

Max Range: 1.1929. Min Range: -1.1929

Max Act: 0.9041. Min Act: -0.0000

Data Index: 1991056 (The Pile)

Max Activating Token Index: 422

Text #14

Max Range: 1.1929. Min Range: -1.1929

Max Act: 0.8617. Min Act: -0.0000

Data Index: 1692527 (The Pile)

Max Activating Token Index: 240

Text #15

Max Range: 1.1929. Min Range: -1.1929

Max Act: 0.8306. Min Act: -0.0000

Data Index: 428846 (The Pile)

Max Activating Token Index: 591

Text #16

Max Range: 1.1929. Min Range: -1.1929

Max Act: 0.9507. Min Act: -0.0000

Data Index: 788606 (The Pile)

Max Activating Token Index: 279

Text #17

Max Range: 1.1929. Min Range: -1.1929

Max Act: 0.7053. Min Act: -0.0000

Data Index: 1590220 (The Pile)

Max Activating Token Index: 153

Text #18

Max Range: 1.1929. Min Range: -1.1929

Max Act: 0.7157. Min Act: -0.0000

Data Index: 1777101 (The Pile)

Max Activating Token Index: 1004

Text #19

Max Range: 1.1929. Min Range: -1.1929

Max Act: 0.5805. Min Act: -0.0000

Data Index: 1911204 (The Pile)

Max Activating Token Index: 892