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

Dataset: The Pile

Neuron 2077 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3679. Min Range: -0.3679

Max Act: 0.3679. Min Act: -0.0000

Data Index: 1573951 (The Pile)

Max Activating Token Index: 9

Text #1

Max Range: 0.3679. Min Range: -0.3679

Max Act: 0.3229. Min Act: -0.0000

Data Index: 1373984 (The Pile)

Max Activating Token Index: 8

Text #2

Max Range: 0.3679. Min Range: -0.3679

Max Act: 0.3229. Min Act: -0.0000

Data Index: 1744815 (The Pile)

Max Activating Token Index: 8

Text #3

Max Range: 0.3679. Min Range: -0.3679

Max Act: 0.3027. Min Act: -0.0000

Data Index: 1590848 (The Pile)

Max Activating Token Index: 9

Text #4

Max Range: 0.3679. Min Range: -0.3679

Max Act: 0.2829. Min Act: -0.0000

Data Index: 880958 (The Pile)

Max Activating Token Index: 257

Text #5

Max Range: 0.3679. Min Range: -0.3679

Max Act: 0.2960. Min Act: -0.0000

Data Index: 476537 (The Pile)

Max Activating Token Index: 54

Text #6

Max Range: 0.3679. Min Range: -0.3679

Max Act: 0.2751. Min Act: -0.0000

Data Index: 1714547 (The Pile)

Max Activating Token Index: 34

Text #7

Max Range: 0.3679. Min Range: -0.3679

Max Act: 0.2633. Min Act: -0.0000

Data Index: 222942 (The Pile)

Max Activating Token Index: 62

Text #8

Max Range: 0.3679. Min Range: -0.3679

Max Act: 0.2668. Min Act: -0.0000

Data Index: 910463 (The Pile)

Max Activating Token Index: 14

Text #9

Max Range: 0.3679. Min Range: -0.3679

Max Act: 0.2562. Min Act: -0.0000

Data Index: 1285318 (The Pile)

Max Activating Token Index: 104

Text #10

Max Range: 0.3679. Min Range: -0.3679

Max Act: 0.2383. Min Act: -0.0000

Data Index: 1199621 (The Pile)

Max Activating Token Index: 35

Text #11

Max Range: 0.3679. Min Range: -0.3679

Max Act: 0.2523. Min Act: -0.0000

Data Index: 208536 (The Pile)

Max Activating Token Index: 37

Text #12

Max Range: 0.3679. Min Range: -0.3679

Max Act: 0.2543. Min Act: -0.0000

Data Index: 274581 (The Pile)

Max Activating Token Index: 61

Text #13

Max Range: 0.3679. Min Range: -0.3679

Max Act: 0.2547. Min Act: -0.0000

Data Index: 1950372 (The Pile)

Max Activating Token Index: 862

Text #14

Max Range: 0.3679. Min Range: -0.3679

Max Act: 0.2374. Min Act: -0.0000

Data Index: 1102362 (The Pile)

Max Activating Token Index: 290

Text #15

Max Range: 0.3679. Min Range: -0.3679

Max Act: 0.2451. Min Act: -0.0000

Data Index: 868543 (The Pile)

Max Activating Token Index: 38

Text #16

Max Range: 0.3679. Min Range: -0.3679

Max Act: 0.2533. Min Act: -0.0000

Data Index: 442249 (The Pile)

Max Activating Token Index: 409

Text #17

Max Range: 0.3679. Min Range: -0.3679

Max Act: 0.2276. Min Act: -0.0000

Data Index: 282183 (The Pile)

Max Activating Token Index: 135

Text #18

Max Range: 0.3679. Min Range: -0.3679

Max Act: 0.2091. Min Act: -0.0000

Data Index: 65716 (The Pile)

Max Activating Token Index: 340

Text #19

Max Range: 0.3679. Min Range: -0.3679

Max Act: 0.2490. Min Act: -0.0000

Data Index: 2190 (The Pile)

Max Activating Token Index: 75