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

Dataset: The Pile

Neuron 3958 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: 1.1854. Min Range: -1.1854

Max Act: 1.1854. Min Act: -0.0000

Data Index: 1582580 (The Pile)

Max Activating Token Index: 85

Text #1

Max Range: 1.1854. Min Range: -1.1854

Max Act: 1.1224. Min Act: -0.0000

Data Index: 1028525 (The Pile)

Max Activating Token Index: 520

Text #2

Max Range: 1.1854. Min Range: -1.1854

Max Act: 1.0724. Min Act: -0.0000

Data Index: 133563 (The Pile)

Max Activating Token Index: 356

Text #3

Max Range: 1.1854. Min Range: -1.1854

Max Act: 1.0297. Min Act: -0.0000

Data Index: 464764 (The Pile)

Max Activating Token Index: 703

Text #4

Max Range: 1.1854. Min Range: -1.1854

Max Act: 0.9882. Min Act: -0.0000

Data Index: 1182795 (The Pile)

Max Activating Token Index: 745

Text #5

Max Range: 1.1854. Min Range: -1.1854

Max Act: 0.8565. Min Act: -0.0000

Data Index: 888472 (The Pile)

Max Activating Token Index: 222

Text #6

Max Range: 1.1854. Min Range: -1.1854

Max Act: 0.8411. Min Act: -0.0000

Data Index: 923998 (The Pile)

Max Activating Token Index: 92

Text #7

Max Range: 1.1854. Min Range: -1.1854

Max Act: 0.8761. Min Act: -0.0000

Data Index: 614178 (The Pile)

Max Activating Token Index: 24

Text #8

Max Range: 1.1854. Min Range: -1.1854

Max Act: 0.8660. Min Act: -0.0000

Data Index: 1734790 (The Pile)

Max Activating Token Index: 426

Text #9

Max Range: 1.1854. Min Range: -1.1854

Max Act: 0.8780. Min Act: -0.0000

Data Index: 676992 (The Pile)

Max Activating Token Index: 489

Text #10

Max Range: 1.1854. Min Range: -1.1854

Max Act: 0.8511. Min Act: -0.0000

Data Index: 1867880 (The Pile)

Max Activating Token Index: 572

Text #11

Max Range: 1.1854. Min Range: -1.1854

Max Act: 0.8651. Min Act: -0.0000

Data Index: 552236 (The Pile)

Max Activating Token Index: 1021

Text #12

Max Range: 1.1854. Min Range: -1.1854

Max Act: 0.8450. Min Act: -0.0000

Data Index: 952537 (The Pile)

Max Activating Token Index: 282

Text #13

Max Range: 1.1854. Min Range: -1.1854

Max Act: 0.8524. Min Act: -0.0000

Data Index: 1580268 (The Pile)

Max Activating Token Index: 895

Text #14

Max Range: 1.1854. Min Range: -1.1854

Max Act: 0.8538. Min Act: -0.0000

Data Index: 1088898 (The Pile)

Max Activating Token Index: 940

Text #15

Max Range: 1.1854. Min Range: -1.1854

Max Act: 0.8341. Min Act: -0.0000

Data Index: 1086677 (The Pile)

Max Activating Token Index: 510

Text #16

Max Range: 1.1854. Min Range: -1.1854

Max Act: 0.8048. Min Act: -0.0000

Data Index: 1039865 (The Pile)

Max Activating Token Index: 991

Text #17

Max Range: 1.1854. Min Range: -1.1854

Max Act: 0.7544. Min Act: -0.0000

Data Index: 324464 (The Pile)

Max Activating Token Index: 624

Text #18

Max Range: 1.1854. Min Range: -1.1854

Max Act: 0.7752. Min Act: -0.0000

Data Index: 679550 (The Pile)

Max Activating Token Index: 308

Text #19

Max Range: 1.1854. Min Range: -1.1854

Max Act: 0.8537. Min Act: -0.0000

Data Index: 1688900 (The Pile)

Max Activating Token Index: 982