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

Dataset: The Pile

Neuron 4640 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: 0.4169. Min Range: -0.4169

Max Act: 0.3906. Min Act: -0.0000

Data Index: 400984 (The Pile)

Max Activating Token Index: 388

Text #1

Max Range: 0.4169. Min Range: -0.4169

Max Act: 0.3729. Min Act: -0.0000

Data Index: 1889578 (The Pile)

Max Activating Token Index: 146

Text #2

Max Range: 0.4169. Min Range: -0.4169

Max Act: 0.3818. Min Act: -0.0000

Data Index: 1172107 (The Pile)

Max Activating Token Index: 291

Text #3

Max Range: 0.4169. Min Range: -0.4169

Max Act: 0.4169. Min Act: -0.0000

Data Index: 949215 (The Pile)

Max Activating Token Index: 613

Text #4

Max Range: 0.4169. Min Range: -0.4169

Max Act: 0.3919. Min Act: -0.0000

Data Index: 1164486 (The Pile)

Max Activating Token Index: 233

Text #5

Max Range: 0.4169. Min Range: -0.4169

Max Act: 0.3987. Min Act: -0.0000

Data Index: 1069328 (The Pile)

Max Activating Token Index: 814

Text #6

Max Range: 0.4169. Min Range: -0.4169

Max Act: 0.3705. Min Act: -0.0000

Data Index: 153347 (The Pile)

Max Activating Token Index: 589

Text #7

Max Range: 0.4169. Min Range: -0.4169

Max Act: 0.3683. Min Act: -0.0000

Data Index: 1469546 (The Pile)

Max Activating Token Index: 621

Text #8

Max Range: 0.4169. Min Range: -0.4169

Max Act: 0.3506. Min Act: -0.0000

Data Index: 130527 (The Pile)

Max Activating Token Index: 55

Text #9

Max Range: 0.4169. Min Range: -0.4169

Max Act: 0.4036. Min Act: -0.0000

Data Index: 1551505 (The Pile)

Max Activating Token Index: 629

Text #10

Max Range: 0.4169. Min Range: -0.4169

Max Act: 0.3691. Min Act: -0.0000

Data Index: 55802 (The Pile)

Max Activating Token Index: 633

Text #11

Max Range: 0.4169. Min Range: -0.4169

Max Act: 0.3453. Min Act: -0.0000

Data Index: 816468 (The Pile)

Max Activating Token Index: 110

Text #12

Max Range: 0.4169. Min Range: -0.4169

Max Act: 0.3495. Min Act: -0.0000

Data Index: 1376488 (The Pile)

Max Activating Token Index: 191

Text #13

Max Range: 0.4169. Min Range: -0.4169

Max Act: 0.3567. Min Act: -0.0000

Data Index: 235422 (The Pile)

Max Activating Token Index: 819

Text #14

Max Range: 0.4169. Min Range: -0.4169

Max Act: 0.3151. Min Act: -0.0000

Data Index: 937580 (The Pile)

Max Activating Token Index: 733

Text #15

Max Range: 0.4169. Min Range: -0.4169

Max Act: 0.3450. Min Act: -0.0000

Data Index: 1584425 (The Pile)

Max Activating Token Index: 161

Text #16

Max Range: 0.4169. Min Range: -0.4169

Max Act: 0.3314. Min Act: -0.0000

Data Index: 1527229 (The Pile)

Max Activating Token Index: 735

Text #17

Max Range: 0.4169. Min Range: -0.4169

Max Act: 0.3523. Min Act: -0.0000

Data Index: 1527590 (The Pile)

Max Activating Token Index: 1011

Text #18

Max Range: 0.4169. Min Range: -0.4169

Max Act: 0.3319. Min Act: -0.0000

Data Index: 1053871 (The Pile)

Max Activating Token Index: 789

Text #19

Max Range: 0.4169. Min Range: -0.4169

Max Act: 0.3675. Min Act: -0.0000

Data Index: 1360040 (The Pile)

Max Activating Token Index: 968