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

Dataset: The Pile

Neuron 639 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.9891. Min Act: -0.0000

Data Index: 425771 (The Pile)

Max Activating Token Index: 325

Text #1

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.9001. Min Act: -0.0000

Data Index: 503141 (The Pile)

Max Activating Token Index: 136

Text #2

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.9414. Min Act: -0.0000

Data Index: 474393 (The Pile)

Max Activating Token Index: 417

Text #3

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.8382. Min Act: -0.0000

Data Index: 1300542 (The Pile)

Max Activating Token Index: 999

Text #4

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.9060. Min Act: -0.0000

Data Index: 883772 (The Pile)

Max Activating Token Index: 869

Text #5

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.8933. Min Act: -0.0000

Data Index: 374645 (The Pile)

Max Activating Token Index: 598

Text #6

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.8491. Min Act: -0.0000

Data Index: 1844853 (The Pile)

Max Activating Token Index: 150

Text #7

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.9276. Min Act: -0.0000

Data Index: 550349 (The Pile)

Max Activating Token Index: 169

Text #8

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.9708. Min Act: -0.0000

Data Index: 1315451 (The Pile)

Max Activating Token Index: 222

Text #9

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.8046. Min Act: -0.0000

Data Index: 112978 (The Pile)

Max Activating Token Index: 479

Text #10

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.8179. Min Act: -0.0000

Data Index: 833787 (The Pile)

Max Activating Token Index: 791

Text #11

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.8104. Min Act: -0.0000

Data Index: 471761 (The Pile)

Max Activating Token Index: 37

Text #12

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.8364. Min Act: -0.0000

Data Index: 730275 (The Pile)

Max Activating Token Index: 1012

Text #13

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.8573. Min Act: -0.0000

Data Index: 367181 (The Pile)

Max Activating Token Index: 723

Text #14

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.8406. Min Act: -0.0000

Data Index: 1018468 (The Pile)

Max Activating Token Index: 834

Text #15

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.8638. Min Act: -0.0000

Data Index: 143766 (The Pile)

Max Activating Token Index: 404

Text #16

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.8077. Min Act: -0.0000

Data Index: 397164 (The Pile)

Max Activating Token Index: 126

Text #17

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.8085. Min Act: -0.0000

Data Index: 63956 (The Pile)

Max Activating Token Index: 104

Text #18

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.7910. Min Act: -0.0000

Data Index: 145535 (The Pile)

Max Activating Token Index: 532

Text #19

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.8280. Min Act: -0.0000

Data Index: 1607666 (The Pile)

Max Activating Token Index: 680