Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3615 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.8404. Min Act: -0.0000

Data Index: 652604 (The Pile)

Max Activating Token Index: 1000

Text #1

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.7818. Min Act: -0.0000

Data Index: 825217 (The Pile)

Max Activating Token Index: 42

Text #2

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.5027. Min Act: -0.0000

Data Index: 34618 (The Pile)

Max Activating Token Index: 68

Text #3

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.4265. Min Act: -0.0000

Data Index: 702735 (The Pile)

Max Activating Token Index: 792

Text #4

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.6141. Min Act: -0.0000

Data Index: 1808834 (The Pile)

Max Activating Token Index: 943

Text #5

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.5031. Min Act: -0.0000

Data Index: 1073064 (The Pile)

Max Activating Token Index: 540

Text #6

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.4857. Min Act: -0.0000

Data Index: 1323940 (The Pile)

Max Activating Token Index: 825

Text #7

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.4476. Min Act: -0.0000

Data Index: 448533 (The Pile)

Max Activating Token Index: 881

Text #8

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.3870. Min Act: -0.0000

Data Index: 114873 (The Pile)

Max Activating Token Index: 914

Text #9

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.3093. Min Act: -0.0000

Data Index: 1149503 (The Pile)

Max Activating Token Index: 133

Text #10

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.3538. Min Act: -0.0000

Data Index: 1550186 (The Pile)

Max Activating Token Index: 725

Text #11

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.3460. Min Act: -0.0000

Data Index: 456560 (The Pile)

Max Activating Token Index: 374

Text #12

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.3462. Min Act: -0.0000

Data Index: 691076 (The Pile)

Max Activating Token Index: 478

Text #13

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.3623. Min Act: -0.0000

Data Index: 1399063 (The Pile)

Max Activating Token Index: 389

Text #14

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.3842. Min Act: -0.0000

Data Index: 1038372 (The Pile)

Max Activating Token Index: 724

Text #15

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.3902. Min Act: -0.0000

Data Index: 628993 (The Pile)

Max Activating Token Index: 1018

Text #16

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.2624. Min Act: -0.0000

Data Index: 1562955 (The Pile)

Max Activating Token Index: 419

Text #17

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.2926. Min Act: -0.0000

Data Index: 62670 (The Pile)

Max Activating Token Index: 255

Text #18

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.1492. Min Act: -0.0000

Data Index: 340171 (The Pile)

Max Activating Token Index: 79

Text #19

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.4789. Min Act: -0.0000

Data Index: 833164 (The Pile)

Max Activating Token Index: 1018