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

Dataset: The Pile

Neuron 2412 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1192. Min Range: -1.1192

Max Act: 1.1192. Min Act: -0.0000

Data Index: 786910 (The Pile)

Max Activating Token Index: 476

Text #1

Max Range: 1.1192. Min Range: -1.1192

Max Act: 1.0299. Min Act: -0.0000

Data Index: 524622 (The Pile)

Max Activating Token Index: 600

Text #2

Max Range: 1.1192. Min Range: -1.1192

Max Act: 1.0073. Min Act: -0.0000

Data Index: 1512885 (The Pile)

Max Activating Token Index: 80

Text #3

Max Range: 1.1192. Min Range: -1.1192

Max Act: 0.9607. Min Act: -0.0000

Data Index: 1254109 (The Pile)

Max Activating Token Index: 727

Text #4

Max Range: 1.1192. Min Range: -1.1192

Max Act: 0.8355. Min Act: -0.0000

Data Index: 1479111 (The Pile)

Max Activating Token Index: 651

Text #5

Max Range: 1.1192. Min Range: -1.1192

Max Act: 0.8901. Min Act: -0.0000

Data Index: 1255524 (The Pile)

Max Activating Token Index: 15

Text #6

Max Range: 1.1192. Min Range: -1.1192

Max Act: 0.8820. Min Act: -0.0000

Data Index: 1426858 (The Pile)

Max Activating Token Index: 731

Text #7

Max Range: 1.1192. Min Range: -1.1192

Max Act: 0.8611. Min Act: -0.0000

Data Index: 949028 (The Pile)

Max Activating Token Index: 615

Text #8

Max Range: 1.1192. Min Range: -1.1192

Max Act: 0.8370. Min Act: 0.0000

Data Index: 574004 (The Pile)

Max Activating Token Index: 299

Text #9

Max Range: 1.1192. Min Range: -1.1192

Max Act: 0.8289. Min Act: -0.0000

Data Index: 1281214 (The Pile)

Max Activating Token Index: 484

Text #10

Max Range: 1.1192. Min Range: -1.1192

Max Act: 0.8216. Min Act: -0.0000

Data Index: 1992695 (The Pile)

Max Activating Token Index: 36

Text #11

Max Range: 1.1192. Min Range: -1.1192

Max Act: 0.8149. Min Act: -0.0000

Data Index: 450307 (The Pile)

Max Activating Token Index: 49

Text #12

Max Range: 1.1192. Min Range: -1.1192

Max Act: 0.8092. Min Act: -0.0000

Data Index: 1357646 (The Pile)

Max Activating Token Index: 731

Text #13

Max Range: 1.1192. Min Range: -1.1192

Max Act: 0.8033. Min Act: -0.0000

Data Index: 455127 (The Pile)

Max Activating Token Index: 166

Text #14

Max Range: 1.1192. Min Range: -1.1192

Max Act: 0.8019. Min Act: -0.0000

Data Index: 482842 (The Pile)

Max Activating Token Index: 313

Text #15

Max Range: 1.1192. Min Range: -1.1192

Max Act: 0.7823. Min Act: -0.0000

Data Index: 926655 (The Pile)

Max Activating Token Index: 217

Text #16

Max Range: 1.1192. Min Range: -1.1192

Max Act: 0.7740. Min Act: -0.0000

Data Index: 882938 (The Pile)

Max Activating Token Index: 792

Text #17

Max Range: 1.1192. Min Range: -1.1192

Max Act: 0.7751. Min Act: 0.0000

Data Index: 809605 (The Pile)

Max Activating Token Index: 342

Text #18

Max Range: 1.1192. Min Range: -1.1192

Max Act: 0.8257. Min Act: -0.0000

Data Index: 1387604 (The Pile)

Max Activating Token Index: 150

Text #19

Max Range: 1.1192. Min Range: -1.1192

Max Act: 0.8107. Min Act: -0.0000

Data Index: 519678 (The Pile)

Max Activating Token Index: 414