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

Dataset: The Pile

Neuron 2922 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6372. Min Range: -1.6372

Max Act: 1.6372. Min Act: -0.0000

Data Index: 854571 (The Pile)

Max Activating Token Index: 322

Text #1

Max Range: 1.6372. Min Range: -1.6372

Max Act: 1.3470. Min Act: -0.0000

Data Index: 935802 (The Pile)

Max Activating Token Index: 362

Text #2

Max Range: 1.6372. Min Range: -1.6372

Max Act: 1.4950. Min Act: -0.0000

Data Index: 1106182 (The Pile)

Max Activating Token Index: 138

Text #3

Max Range: 1.6372. Min Range: -1.6372

Max Act: 1.3033. Min Act: -0.0000

Data Index: 137102 (The Pile)

Max Activating Token Index: 265

Text #4

Max Range: 1.6372. Min Range: -1.6372

Max Act: 1.2926. Min Act: -0.0000

Data Index: 1681706 (The Pile)

Max Activating Token Index: 366

Text #5

Max Range: 1.6372. Min Range: -1.6372

Max Act: 1.2925. Min Act: -0.0000

Data Index: 290483 (The Pile)

Max Activating Token Index: 516

Text #6

Max Range: 1.6372. Min Range: -1.6372

Max Act: 1.2671. Min Act: -0.0000

Data Index: 1678255 (The Pile)

Max Activating Token Index: 990

Text #7

Max Range: 1.6372. Min Range: -1.6372

Max Act: 1.2358. Min Act: -0.0000

Data Index: 1781672 (The Pile)

Max Activating Token Index: 904

Text #8

Max Range: 1.6372. Min Range: -1.6372

Max Act: 1.2901. Min Act: -0.0000

Data Index: 1046455 (The Pile)

Max Activating Token Index: 443

Text #9

Max Range: 1.6372. Min Range: -1.6372

Max Act: 1.2776. Min Act: -0.0000

Data Index: 1196368 (The Pile)

Max Activating Token Index: 905

Text #10

Max Range: 1.6372. Min Range: -1.6372

Max Act: 1.1713. Min Act: -0.0000

Data Index: 769621 (The Pile)

Max Activating Token Index: 862

Text #11

Max Range: 1.6372. Min Range: -1.6372

Max Act: 1.1813. Min Act: -0.0000

Data Index: 214667 (The Pile)

Max Activating Token Index: 729

Text #12

Max Range: 1.6372. Min Range: -1.6372

Max Act: 1.1689. Min Act: -0.0000

Data Index: 810365 (The Pile)

Max Activating Token Index: 287

Text #13

Max Range: 1.6372. Min Range: -1.6372

Max Act: 1.3098. Min Act: -0.0000

Data Index: 1018484 (The Pile)

Max Activating Token Index: 964

Text #14

Max Range: 1.6372. Min Range: -1.6372

Max Act: 1.0888. Min Act: -0.0000

Data Index: 138045 (The Pile)

Max Activating Token Index: 74

Text #15

Max Range: 1.6372. Min Range: -1.6372

Max Act: 1.0839. Min Act: -0.0000

Data Index: 617108 (The Pile)

Max Activating Token Index: 584

Text #16

Max Range: 1.6372. Min Range: -1.6372

Max Act: 1.2078. Min Act: -0.0000

Data Index: 54797 (The Pile)

Max Activating Token Index: 782

Text #17

Max Range: 1.6372. Min Range: -1.6372

Max Act: 1.1712. Min Act: -0.0000

Data Index: 939384 (The Pile)

Max Activating Token Index: 680

Text #18

Max Range: 1.6372. Min Range: -1.6372

Max Act: 1.0994. Min Act: -0.0000

Data Index: 358958 (The Pile)

Max Activating Token Index: 49

Text #19

Max Range: 1.6372. Min Range: -1.6372

Max Act: 1.1906. Min Act: -0.0000

Data Index: 1047366 (The Pile)

Max Activating Token Index: 715