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

Dataset: The Pile

Neuron 4460 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1932. Min Range: -1.1932

Max Act: 1.1932. Min Act: -0.0000

Data Index: 1351701 (The Pile)

Max Activating Token Index: 513

Text #1

Max Range: 1.1932. Min Range: -1.1932

Max Act: 1.0169. Min Act: -0.0000

Data Index: 546061 (The Pile)

Max Activating Token Index: 983

Text #2

Max Range: 1.1932. Min Range: -1.1932

Max Act: 1.1340. Min Act: -0.0000

Data Index: 281445 (The Pile)

Max Activating Token Index: 269

Text #3

Max Range: 1.1932. Min Range: -1.1932

Max Act: 0.7604. Min Act: -0.0000

Data Index: 1863207 (The Pile)

Max Activating Token Index: 794

Text #4

Max Range: 1.1932. Min Range: -1.1932

Max Act: 1.0546. Min Act: -0.0000

Data Index: 994183 (The Pile)

Max Activating Token Index: 550

Text #5

Max Range: 1.1932. Min Range: -1.1932

Max Act: 1.0549. Min Act: -0.0000

Data Index: 1381579 (The Pile)

Max Activating Token Index: 269

Text #6

Max Range: 1.1932. Min Range: -1.1932

Max Act: 0.9544. Min Act: -0.0000

Data Index: 194796 (The Pile)

Max Activating Token Index: 823

Text #7

Max Range: 1.1932. Min Range: -1.1932

Max Act: 0.9446. Min Act: -0.0000

Data Index: 1075192 (The Pile)

Max Activating Token Index: 171

Text #8

Max Range: 1.1932. Min Range: -1.1932

Max Act: 0.9983. Min Act: -0.0000

Data Index: 485886 (The Pile)

Max Activating Token Index: 664

Text #9

Max Range: 1.1932. Min Range: -1.1932

Max Act: 0.9313. Min Act: -0.0000

Data Index: 414176 (The Pile)

Max Activating Token Index: 32

Text #10

Max Range: 1.1932. Min Range: -1.1932

Max Act: 0.9351. Min Act: -0.0000

Data Index: 1562325 (The Pile)

Max Activating Token Index: 649

Text #11

Max Range: 1.1932. Min Range: -1.1932

Max Act: 0.9288. Min Act: -0.0000

Data Index: 1816544 (The Pile)

Max Activating Token Index: 598

Text #12

Max Range: 1.1932. Min Range: -1.1932

Max Act: 0.9723. Min Act: -0.0000

Data Index: 1239396 (The Pile)

Max Activating Token Index: 703

Text #13

Max Range: 1.1932. Min Range: -1.1932

Max Act: 1.0332. Min Act: -0.0000

Data Index: 1919482 (The Pile)

Max Activating Token Index: 323

Text #14

Max Range: 1.1932. Min Range: -1.1932

Max Act: 0.9009. Min Act: -0.0000

Data Index: 1525725 (The Pile)

Max Activating Token Index: 956

Text #15

Max Range: 1.1932. Min Range: -1.1932

Max Act: 0.9538. Min Act: -0.0000

Data Index: 56336 (The Pile)

Max Activating Token Index: 566

Text #16

Max Range: 1.1932. Min Range: -1.1932

Max Act: 1.0168. Min Act: -0.0000

Data Index: 1447419 (The Pile)

Max Activating Token Index: 344

Text #17

Max Range: 1.1932. Min Range: -1.1932

Max Act: 0.9421. Min Act: -0.0000

Data Index: 715849 (The Pile)

Max Activating Token Index: 987

Text #18

Max Range: 1.1932. Min Range: -1.1932

Max Act: 0.9497. Min Act: -0.0000

Data Index: 1672096 (The Pile)

Max Activating Token Index: 462

Text #19

Max Range: 1.1932. Min Range: -1.1932

Max Act: 1.0028. Min Act: -0.0000

Data Index: 538384 (The Pile)

Max Activating Token Index: 57