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

Dataset: The Pile

Neuron 1672 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: 0.3584. Min Range: -0.3584

Max Act: 0.3584. Min Act: -0.0000

Data Index: 629781 (The Pile)

Max Activating Token Index: 474

Text #1

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.3464. Min Act: -0.0000

Data Index: 1048709 (The Pile)

Max Activating Token Index: 358

Text #2

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.3424. Min Act: -0.0000

Data Index: 1000522 (The Pile)

Max Activating Token Index: 767

Text #3

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.3583. Min Act: -0.0000

Data Index: 489800 (The Pile)

Max Activating Token Index: 348

Text #4

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.3424. Min Act: -0.0000

Data Index: 1836311 (The Pile)

Max Activating Token Index: 484

Text #5

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.3349. Min Act: -0.0000

Data Index: 1387963 (The Pile)

Max Activating Token Index: 782

Text #6

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.3199. Min Act: -0.0000

Data Index: 1137524 (The Pile)

Max Activating Token Index: 831

Text #7

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2906. Min Act: -0.0000

Data Index: 1043021 (The Pile)

Max Activating Token Index: 686

Text #8

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2799. Min Act: -0.0000

Data Index: 330901 (The Pile)

Max Activating Token Index: 411

Text #9

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2783. Min Act: -0.0000

Data Index: 52876 (The Pile)

Max Activating Token Index: 535

Text #10

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2678. Min Act: -0.0000

Data Index: 1325638 (The Pile)

Max Activating Token Index: 383

Text #11

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2693. Min Act: -0.0000

Data Index: 562853 (The Pile)

Max Activating Token Index: 984

Text #12

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2545. Min Act: -0.0000

Data Index: 1800263 (The Pile)

Max Activating Token Index: 117

Text #13

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2806. Min Act: -0.0000

Data Index: 1477626 (The Pile)

Max Activating Token Index: 119

Text #14

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2606. Min Act: -0.0000

Data Index: 1305565 (The Pile)

Max Activating Token Index: 619

Text #15

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2733. Min Act: -0.0000

Data Index: 1630145 (The Pile)

Max Activating Token Index: 708

Text #16

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2726. Min Act: -0.0000

Data Index: 1321249 (The Pile)

Max Activating Token Index: 111

Text #17

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2522. Min Act: -0.0000

Data Index: 330732 (The Pile)

Max Activating Token Index: 533

Text #18

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2624. Min Act: -0.0000

Data Index: 329430 (The Pile)

Max Activating Token Index: 192

Text #19

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2391. Min Act: -0.0000

Data Index: 777486 (The Pile)

Max Activating Token Index: 444