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

Dataset: The Pile

Neuron 371 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: 1.2944. Min Range: -1.2944

Max Act: 1.2944. Min Act: -0.0000

Data Index: 337786 (The Pile)

Max Activating Token Index: 296

Text #1

Max Range: 1.2944. Min Range: -1.2944

Max Act: 1.2112. Min Act: -0.0000

Data Index: 1277944 (The Pile)

Max Activating Token Index: 653

Text #2

Max Range: 1.2944. Min Range: -1.2944

Max Act: 1.1889. Min Act: -0.0000

Data Index: 736866 (The Pile)

Max Activating Token Index: 151

Text #3

Max Range: 1.2944. Min Range: -1.2944

Max Act: 1.2519. Min Act: -0.0000

Data Index: 962224 (The Pile)

Max Activating Token Index: 255

Text #4

Max Range: 1.2944. Min Range: -1.2944

Max Act: 1.0968. Min Act: -0.0000

Data Index: 82613 (The Pile)

Max Activating Token Index: 443

Text #5

Max Range: 1.2944. Min Range: -1.2944

Max Act: 1.0679. Min Act: -0.0000

Data Index: 1253333 (The Pile)

Max Activating Token Index: 236

Text #6

Max Range: 1.2944. Min Range: -1.2944

Max Act: 1.0971. Min Act: -0.0000

Data Index: 1572588 (The Pile)

Max Activating Token Index: 603

Text #7

Max Range: 1.2944. Min Range: -1.2944

Max Act: 1.0981. Min Act: -0.0000

Data Index: 1616434 (The Pile)

Max Activating Token Index: 784

Text #8

Max Range: 1.2944. Min Range: -1.2944

Max Act: 1.0929. Min Act: -0.0000

Data Index: 1861926 (The Pile)

Max Activating Token Index: 426

Text #9

Max Range: 1.2944. Min Range: -1.2944

Max Act: 1.1734. Min Act: -0.0000

Data Index: 1886249 (The Pile)

Max Activating Token Index: 14

Text #10

Max Range: 1.2944. Min Range: -1.2944

Max Act: 1.0037. Min Act: -0.0000

Data Index: 1884395 (The Pile)

Max Activating Token Index: 917

Text #11

Max Range: 1.2944. Min Range: -1.2944

Max Act: 1.0681. Min Act: -0.0000

Data Index: 1301828 (The Pile)

Max Activating Token Index: 568

Text #12

Max Range: 1.2944. Min Range: -1.2944

Max Act: 1.0061. Min Act: -0.0000

Data Index: 1360933 (The Pile)

Max Activating Token Index: 1018

Text #13

Max Range: 1.2944. Min Range: -1.2944

Max Act: 0.9912. Min Act: -0.0000

Data Index: 9581 (The Pile)

Max Activating Token Index: 196

Text #14

Max Range: 1.2944. Min Range: -1.2944

Max Act: 1.0428. Min Act: -0.0000

Data Index: 503373 (The Pile)

Max Activating Token Index: 922

Text #15

Max Range: 1.2944. Min Range: -1.2944

Max Act: 0.9566. Min Act: -0.0000

Data Index: 929605 (The Pile)

Max Activating Token Index: 491

Text #16

Max Range: 1.2944. Min Range: -1.2944

Max Act: 1.0819. Min Act: -0.0000

Data Index: 1894344 (The Pile)

Max Activating Token Index: 95

Text #17

Max Range: 1.2944. Min Range: -1.2944

Max Act: 1.1231. Min Act: -0.0000

Data Index: 1414077 (The Pile)

Max Activating Token Index: 570

Text #18

Max Range: 1.2944. Min Range: -1.2944

Max Act: 0.9328. Min Act: -0.0000

Data Index: 765084 (The Pile)

Max Activating Token Index: 611

Text #19

Max Range: 1.2944. Min Range: -1.2944

Max Act: 0.9912. Min Act: -0.0000

Data Index: 1494517 (The Pile)

Max Activating Token Index: 363