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

Dataset: The Pile

Neuron 617 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3523. Min Range: -1.3523

Max Act: 1.3523. Min Act: -0.0000

Data Index: 1942547 (The Pile)

Max Activating Token Index: 921

Text #1

Max Range: 1.3523. Min Range: -1.3523

Max Act: 1.3006. Min Act: -0.0000

Data Index: 659083 (The Pile)

Max Activating Token Index: 1011

Text #2

Max Range: 1.3523. Min Range: -1.3523

Max Act: 1.3026. Min Act: -0.0000

Data Index: 454372 (The Pile)

Max Activating Token Index: 469

Text #3

Max Range: 1.3523. Min Range: -1.3523

Max Act: 1.2015. Min Act: -0.0000

Data Index: 1970972 (The Pile)

Max Activating Token Index: 149

Text #4

Max Range: 1.3523. Min Range: -1.3523

Max Act: 1.1954. Min Act: -0.0000

Data Index: 1732231 (The Pile)

Max Activating Token Index: 40

Text #5

Max Range: 1.3523. Min Range: -1.3523

Max Act: 1.1194. Min Act: -0.0000

Data Index: 1250449 (The Pile)

Max Activating Token Index: 510

Text #6

Max Range: 1.3523. Min Range: -1.3523

Max Act: 1.2528. Min Act: -0.0000

Data Index: 206774 (The Pile)

Max Activating Token Index: 1020

Text #7

Max Range: 1.3523. Min Range: -1.3523

Max Act: 1.1760. Min Act: -0.0000

Data Index: 660582 (The Pile)

Max Activating Token Index: 817

Text #8

Max Range: 1.3523. Min Range: -1.3523

Max Act: 1.0886. Min Act: -0.0000

Data Index: 685285 (The Pile)

Max Activating Token Index: 1021

Text #9

Max Range: 1.3523. Min Range: -1.3523

Max Act: 1.1632. Min Act: -0.0000

Data Index: 1635042 (The Pile)

Max Activating Token Index: 356

Text #10

Max Range: 1.3523. Min Range: -1.3523

Max Act: 1.0860. Min Act: -0.0000

Data Index: 1596318 (The Pile)

Max Activating Token Index: 654

Text #11

Max Range: 1.3523. Min Range: -1.3523

Max Act: 1.0522. Min Act: -0.0000

Data Index: 314352 (The Pile)

Max Activating Token Index: 261

Text #12

Max Range: 1.3523. Min Range: -1.3523

Max Act: 1.0561. Min Act: -0.0000

Data Index: 1502877 (The Pile)

Max Activating Token Index: 574

Text #13

Max Range: 1.3523. Min Range: -1.3523

Max Act: 1.0719. Min Act: -0.0000

Data Index: 826966 (The Pile)

Max Activating Token Index: 117

Text #14

Max Range: 1.3523. Min Range: -1.3523

Max Act: 1.0163. Min Act: -0.0000

Data Index: 1238725 (The Pile)

Max Activating Token Index: 842

Text #15

Max Range: 1.3523. Min Range: -1.3523

Max Act: 1.0318. Min Act: -0.0000

Data Index: 1912784 (The Pile)

Max Activating Token Index: 984

Text #16

Max Range: 1.3523. Min Range: -1.3523

Max Act: 1.1230. Min Act: -0.0000

Data Index: 333600 (The Pile)

Max Activating Token Index: 833

Text #17

Max Range: 1.3523. Min Range: -1.3523

Max Act: 0.9791. Min Act: -0.0000

Data Index: 1911186 (The Pile)

Max Activating Token Index: 37

Text #18

Max Range: 1.3523. Min Range: -1.3523

Max Act: 1.0121. Min Act: -0.0000

Data Index: 1127230 (The Pile)

Max Activating Token Index: 153

Text #19

Max Range: 1.3523. Min Range: -1.3523

Max Act: 0.9834. Min Act: -0.0000

Data Index: 504864 (The Pile)

Max Activating Token Index: 237