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

Dataset: The Pile

Neuron 2708 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.3309. Min Act: -0.0000

Data Index: 1027438 (The Pile)

Max Activating Token Index: 624

Text #1

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.3037. Min Act: -0.0000

Data Index: 1159012 (The Pile)

Max Activating Token Index: 643

Text #2

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.3112. Min Act: -0.0000

Data Index: 1246658 (The Pile)

Max Activating Token Index: 70

Text #3

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.3213. Min Act: -0.0000

Data Index: 1748871 (The Pile)

Max Activating Token Index: 427

Text #4

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.2942. Min Act: -0.0000

Data Index: 1586968 (The Pile)

Max Activating Token Index: 640

Text #5

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.2766. Min Act: -0.0000

Data Index: 1109054 (The Pile)

Max Activating Token Index: 490

Text #6

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.3022. Min Act: -0.0000

Data Index: 285565 (The Pile)

Max Activating Token Index: 519

Text #7

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.2607. Min Act: -0.0000

Data Index: 33843 (The Pile)

Max Activating Token Index: 727

Text #8

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.3004. Min Act: -0.0000

Data Index: 924566 (The Pile)

Max Activating Token Index: 912

Text #9

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.2354. Min Act: -0.0000

Data Index: 1457908 (The Pile)

Max Activating Token Index: 924

Text #10

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.2741. Min Act: -0.0000

Data Index: 944233 (The Pile)

Max Activating Token Index: 629

Text #11

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.2835. Min Act: -0.0000

Data Index: 302558 (The Pile)

Max Activating Token Index: 435

Text #12

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.2677. Min Act: -0.0000

Data Index: 1601968 (The Pile)

Max Activating Token Index: 651

Text #13

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.2590. Min Act: -0.0000

Data Index: 1234345 (The Pile)

Max Activating Token Index: 788

Text #14

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.2470. Min Act: -0.0000

Data Index: 337422 (The Pile)

Max Activating Token Index: 652

Text #15

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.2763. Min Act: -0.0000

Data Index: 1060726 (The Pile)

Max Activating Token Index: 276

Text #16

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.2507. Min Act: -0.0000

Data Index: 1910768 (The Pile)

Max Activating Token Index: 758

Text #17

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.2689. Min Act: -0.0000

Data Index: 1455373 (The Pile)

Max Activating Token Index: 639

Text #18

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.2949. Min Act: -0.0000

Data Index: 86524 (The Pile)

Max Activating Token Index: 623

Text #19

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.2688. Min Act: -0.0000

Data Index: 870784 (The Pile)

Max Activating Token Index: 943