Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2235 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.6915. Min Act: -0.0000

Data Index: 502289 (The Pile)

Max Activating Token Index: 800

Text #1

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.5994. Min Act: -0.0000

Data Index: 1564447 (The Pile)

Max Activating Token Index: 724

Text #2

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.5610. Min Act: -0.0000

Data Index: 1504130 (The Pile)

Max Activating Token Index: 246

Text #3

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.5582. Min Act: -0.0000

Data Index: 715690 (The Pile)

Max Activating Token Index: 368

Text #4

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.5206. Min Act: -0.0000

Data Index: 771536 (The Pile)

Max Activating Token Index: 666

Text #5

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.5859. Min Act: -0.0000

Data Index: 998452 (The Pile)

Max Activating Token Index: 63

Text #6

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.5476. Min Act: -0.0000

Data Index: 586776 (The Pile)

Max Activating Token Index: 514

Text #7

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.5083. Min Act: -0.0000

Data Index: 1890855 (The Pile)

Max Activating Token Index: 1019

Text #8

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.4819. Min Act: -0.0000

Data Index: 260481 (The Pile)

Max Activating Token Index: 272

Text #9

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.4807. Min Act: -0.0000

Data Index: 637960 (The Pile)

Max Activating Token Index: 603

Text #10

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.4760. Min Act: -0.0000

Data Index: 530402 (The Pile)

Max Activating Token Index: 467

Text #11

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.4995. Min Act: -0.0000

Data Index: 750706 (The Pile)

Max Activating Token Index: 418

Text #12

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.4629. Min Act: -0.0000

Data Index: 1162521 (The Pile)

Max Activating Token Index: 42

Text #13

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.4442. Min Act: -0.0000

Data Index: 382565 (The Pile)

Max Activating Token Index: 842

Text #14

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.4331. Min Act: -0.0000

Data Index: 739274 (The Pile)

Max Activating Token Index: 458

Text #15

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.4511. Min Act: -0.0000

Data Index: 98805 (The Pile)

Max Activating Token Index: 574

Text #16

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.4510. Min Act: -0.0000

Data Index: 513711 (The Pile)

Max Activating Token Index: 966

Text #17

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.4097. Min Act: -0.0000

Data Index: 543267 (The Pile)

Max Activating Token Index: 537

Text #18

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.4395. Min Act: -0.0000

Data Index: 470957 (The Pile)

Max Activating Token Index: 474

Text #19

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.4493. Min Act: -0.0000

Data Index: 1229928 (The Pile)

Max Activating Token Index: 431