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

Dataset: The Pile

Neuron 883 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: 0.5864. Min Range: -0.5864

Max Act: 0.5864. Min Act: -0.0000

Data Index: 438611 (The Pile)

Max Activating Token Index: 547

Text #1

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.4672. Min Act: -0.0000

Data Index: 856534 (The Pile)

Max Activating Token Index: 925

Text #2

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.4309. Min Act: 0.0000

Data Index: 1752017 (The Pile)

Max Activating Token Index: 462

Text #3

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.3877. Min Act: -0.0000

Data Index: 465105 (The Pile)

Max Activating Token Index: 362

Text #4

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.4022. Min Act: -0.0000

Data Index: 1061205 (The Pile)

Max Activating Token Index: 145

Text #5

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.3769. Min Act: -0.0000

Data Index: 1899188 (The Pile)

Max Activating Token Index: 535

Text #6

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.3671. Min Act: -0.0000

Data Index: 1310842 (The Pile)

Max Activating Token Index: 497

Text #7

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.3485. Min Act: -0.0000

Data Index: 96541 (The Pile)

Max Activating Token Index: 433

Text #8

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.3913. Min Act: -0.0000

Data Index: 1205969 (The Pile)

Max Activating Token Index: 279

Text #9

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.3954. Min Act: -0.0000

Data Index: 1144432 (The Pile)

Max Activating Token Index: 141

Text #10

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.3885. Min Act: 0.0000

Data Index: 194324 (The Pile)

Max Activating Token Index: 239

Text #11

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.3884. Min Act: -0.0000

Data Index: 521897 (The Pile)

Max Activating Token Index: 949

Text #12

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.3635. Min Act: -0.0000

Data Index: 466678 (The Pile)

Max Activating Token Index: 746

Text #13

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.3371. Min Act: -0.0000

Data Index: 1930886 (The Pile)

Max Activating Token Index: 939

Text #14

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.3656. Min Act: -0.0000

Data Index: 1934641 (The Pile)

Max Activating Token Index: 823

Text #15

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.3555. Min Act: -0.0000

Data Index: 628189 (The Pile)

Max Activating Token Index: 401

Text #16

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.3536. Min Act: -0.0000

Data Index: 1757774 (The Pile)

Max Activating Token Index: 106

Text #17

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.3520. Min Act: -0.0000

Data Index: 1898638 (The Pile)

Max Activating Token Index: 696

Text #18

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.3462. Min Act: -0.0000

Data Index: 1158612 (The Pile)

Max Activating Token Index: 593

Text #19

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.3544. Min Act: -0.0000

Data Index: 1131654 (The Pile)

Max Activating Token Index: 23