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

Dataset: The Pile

Neuron 3556 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: 0.7463. Min Range: -0.7463

Max Act: 0.7463. Min Act: -0.0000

Data Index: 717307 (The Pile)

Max Activating Token Index: 829

Text #1

Max Range: 0.7463. Min Range: -0.7463

Max Act: 0.6308. Min Act: -0.0000

Data Index: 56850 (The Pile)

Max Activating Token Index: 149

Text #2

Max Range: 0.7463. Min Range: -0.7463

Max Act: 0.6174. Min Act: -0.0000

Data Index: 1827950 (The Pile)

Max Activating Token Index: 425

Text #3

Max Range: 0.7463. Min Range: -0.7463

Max Act: 0.5415. Min Act: -0.0000

Data Index: 1037157 (The Pile)

Max Activating Token Index: 102

Text #4

Max Range: 0.7463. Min Range: -0.7463

Max Act: 0.5568. Min Act: -0.0000

Data Index: 361084 (The Pile)

Max Activating Token Index: 780

Text #5

Max Range: 0.7463. Min Range: -0.7463

Max Act: 0.5378. Min Act: -0.0000

Data Index: 119390 (The Pile)

Max Activating Token Index: 71

Text #6

Max Range: 0.7463. Min Range: -0.7463

Max Act: 0.5165. Min Act: -0.0000

Data Index: 918087 (The Pile)

Max Activating Token Index: 559

Text #7

Max Range: 0.7463. Min Range: -0.7463

Max Act: 0.5206. Min Act: -0.0000

Data Index: 1223531 (The Pile)

Max Activating Token Index: 897

Text #8

Max Range: 0.7463. Min Range: -0.7463

Max Act: 0.5516. Min Act: -0.0000

Data Index: 1803726 (The Pile)

Max Activating Token Index: 797

Text #9

Max Range: 0.7463. Min Range: -0.7463

Max Act: 0.4936. Min Act: -0.0000

Data Index: 889839 (The Pile)

Max Activating Token Index: 523

Text #10

Max Range: 0.7463. Min Range: -0.7463

Max Act: 0.5134. Min Act: -0.0000

Data Index: 1730744 (The Pile)

Max Activating Token Index: 456

Text #11

Max Range: 0.7463. Min Range: -0.7463

Max Act: 0.5128. Min Act: -0.0000

Data Index: 11458 (The Pile)

Max Activating Token Index: 677

Text #12

Max Range: 0.7463. Min Range: -0.7463

Max Act: 0.4949. Min Act: -0.0000

Data Index: 1493889 (The Pile)

Max Activating Token Index: 143

Text #13

Max Range: 0.7463. Min Range: -0.7463

Max Act: 0.4336. Min Act: -0.0000

Data Index: 1230357 (The Pile)

Max Activating Token Index: 676

Text #14

Max Range: 0.7463. Min Range: -0.7463

Max Act: 0.4512. Min Act: -0.0000

Data Index: 1976024 (The Pile)

Max Activating Token Index: 718

Text #15

Max Range: 0.7463. Min Range: -0.7463

Max Act: 0.5003. Min Act: -0.0000

Data Index: 576786 (The Pile)

Max Activating Token Index: 827

Text #16

Max Range: 0.7463. Min Range: -0.7463

Max Act: 0.4674. Min Act: -0.0000

Data Index: 1828945 (The Pile)

Max Activating Token Index: 879

Text #17

Max Range: 0.7463. Min Range: -0.7463

Max Act: 0.4673. Min Act: -0.0000

Data Index: 779462 (The Pile)

Max Activating Token Index: 785

Text #18

Max Range: 0.7463. Min Range: -0.7463

Max Act: 0.4486. Min Act: -0.0000

Data Index: 836724 (The Pile)

Max Activating Token Index: 29

Text #19

Max Range: 0.7463. Min Range: -0.7463

Max Act: 0.4307. Min Act: -0.0000

Data Index: 103 (The Pile)

Max Activating Token Index: 41