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

Dataset: The Pile

Neuron 3000 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: 1.1138. Min Range: -1.1138

Max Act: 1.0872. Min Act: -0.0000

Data Index: 1182701 (The Pile)

Max Activating Token Index: 480

Text #1

Max Range: 1.1138. Min Range: -1.1138

Max Act: 1.1138. Min Act: -0.0000

Data Index: 652968 (The Pile)

Max Activating Token Index: 941

Text #2

Max Range: 1.1138. Min Range: -1.1138

Max Act: 1.0427. Min Act: -0.0000

Data Index: 216800 (The Pile)

Max Activating Token Index: 277

Text #3

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.9712. Min Act: -0.0000

Data Index: 1508228 (The Pile)

Max Activating Token Index: 670

Text #4

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.9104. Min Act: -0.0000

Data Index: 51458 (The Pile)

Max Activating Token Index: 788

Text #5

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.9489. Min Act: -0.0000

Data Index: 176131 (The Pile)

Max Activating Token Index: 872

Text #6

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.8900. Min Act: -0.0000

Data Index: 950424 (The Pile)

Max Activating Token Index: 870

Text #7

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.8905. Min Act: -0.0000

Data Index: 1592915 (The Pile)

Max Activating Token Index: 921

Text #8

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.8833. Min Act: -0.0000

Data Index: 989748 (The Pile)

Max Activating Token Index: 941

Text #9

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.8217. Min Act: -0.0000

Data Index: 1420368 (The Pile)

Max Activating Token Index: 635

Text #10

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.9088. Min Act: -0.0000

Data Index: 1596885 (The Pile)

Max Activating Token Index: 407

Text #11

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.8794. Min Act: -0.0000

Data Index: 13041 (The Pile)

Max Activating Token Index: 761

Text #12

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.8623. Min Act: -0.0000

Data Index: 1395492 (The Pile)

Max Activating Token Index: 209

Text #13

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.9206. Min Act: -0.0000

Data Index: 1753822 (The Pile)

Max Activating Token Index: 1001

Text #14

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.8407. Min Act: -0.0000

Data Index: 1797136 (The Pile)

Max Activating Token Index: 932

Text #15

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.9011. Min Act: -0.0000

Data Index: 583046 (The Pile)

Max Activating Token Index: 571

Text #16

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.8931. Min Act: -0.0000

Data Index: 1441737 (The Pile)

Max Activating Token Index: 60

Text #17

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.8858. Min Act: -0.0000

Data Index: 609698 (The Pile)

Max Activating Token Index: 283

Text #18

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.8333. Min Act: -0.0000

Data Index: 733115 (The Pile)

Max Activating Token Index: 718

Text #19

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.8432. Min Act: -0.0000

Data Index: 857089 (The Pile)

Max Activating Token Index: 713