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

Dataset: The Pile

Neuron 3549 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: 0.6385. Min Range: -0.6385

Max Act: 0.6385. Min Act: -0.0000

Data Index: 1891737 (The Pile)

Max Activating Token Index: 904

Text #1

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.5666. Min Act: -0.0000

Data Index: 739941 (The Pile)

Max Activating Token Index: 780

Text #2

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.4707. Min Act: -0.0000

Data Index: 1008546 (The Pile)

Max Activating Token Index: 775

Text #3

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.4971. Min Act: -0.0000

Data Index: 34317 (The Pile)

Max Activating Token Index: 970

Text #4

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.5200. Min Act: -0.0000

Data Index: 460988 (The Pile)

Max Activating Token Index: 490

Text #5

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.4944. Min Act: -0.0000

Data Index: 29980 (The Pile)

Max Activating Token Index: 145

Text #6

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.4904. Min Act: -0.0000

Data Index: 1096061 (The Pile)

Max Activating Token Index: 355

Text #7

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.4486. Min Act: -0.0000

Data Index: 1215944 (The Pile)

Max Activating Token Index: 964

Text #8

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.4827. Min Act: -0.0000

Data Index: 1887898 (The Pile)

Max Activating Token Index: 569

Text #9

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.4604. Min Act: -0.0000

Data Index: 1875045 (The Pile)

Max Activating Token Index: 148

Text #10

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.4948. Min Act: -0.0000

Data Index: 1588412 (The Pile)

Max Activating Token Index: 163

Text #11

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.4608. Min Act: -0.0000

Data Index: 958355 (The Pile)

Max Activating Token Index: 883

Text #12

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.4629. Min Act: -0.0000

Data Index: 3422 (The Pile)

Max Activating Token Index: 455

Text #13

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.4593. Min Act: -0.0000

Data Index: 1081222 (The Pile)

Max Activating Token Index: 691

Text #14

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.4596. Min Act: -0.0000

Data Index: 444077 (The Pile)

Max Activating Token Index: 114

Text #15

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.4661. Min Act: -0.0000

Data Index: 625906 (The Pile)

Max Activating Token Index: 984

Text #16

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.4052. Min Act: -0.0000

Data Index: 757260 (The Pile)

Max Activating Token Index: 931

Text #17

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.4500. Min Act: -0.0000

Data Index: 1882204 (The Pile)

Max Activating Token Index: 271

Text #18

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.4559. Min Act: -0.0000

Data Index: 141451 (The Pile)

Max Activating Token Index: 827

Text #19

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.4601. Min Act: -0.0000

Data Index: 1076237 (The Pile)

Max Activating Token Index: 640