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

Dataset: The Pile

Neuron 2113 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: 3.1910. Min Range: -3.1910

Max Act: 3.1910. Min Act: 0.0000

Data Index: 781284 (The Pile)

Max Activating Token Index: 820

Text #1

Max Range: 3.1910. Min Range: -3.1910

Max Act: 2.8246. Min Act: -0.0000

Data Index: 448879 (The Pile)

Max Activating Token Index: 274

Text #2

Max Range: 3.1910. Min Range: -3.1910

Max Act: 2.9196. Min Act: -0.0000

Data Index: 1923616 (The Pile)

Max Activating Token Index: 940

Text #3

Max Range: 3.1910. Min Range: -3.1910

Max Act: 2.7539. Min Act: -0.0000

Data Index: 1775096 (The Pile)

Max Activating Token Index: 954

Text #4

Max Range: 3.1910. Min Range: -3.1910

Max Act: 2.7589. Min Act: -0.0000

Data Index: 424890 (The Pile)

Max Activating Token Index: 240

Text #5

Max Range: 3.1910. Min Range: -3.1910

Max Act: 2.7138. Min Act: -0.0000

Data Index: 1214605 (The Pile)

Max Activating Token Index: 355

Text #6

Max Range: 3.1910. Min Range: -3.1910

Max Act: 2.7065. Min Act: -0.0000

Data Index: 951716 (The Pile)

Max Activating Token Index: 750

Text #7

Max Range: 3.1910. Min Range: -3.1910

Max Act: 2.5312. Min Act: -0.0000

Data Index: 1707221 (The Pile)

Max Activating Token Index: 325

Text #8

Max Range: 3.1910. Min Range: -3.1910

Max Act: 2.8341. Min Act: -0.0000

Data Index: 11579 (The Pile)

Max Activating Token Index: 184

Text #9

Max Range: 3.1910. Min Range: -3.1910

Max Act: 2.8504. Min Act: -0.0000

Data Index: 185044 (The Pile)

Max Activating Token Index: 958

Text #10

Max Range: 3.1910. Min Range: -3.1910

Max Act: 2.7062. Min Act: -0.0000

Data Index: 810775 (The Pile)

Max Activating Token Index: 610

Text #11

Max Range: 3.1910. Min Range: -3.1910

Max Act: 2.6234. Min Act: 0.0000

Data Index: 1786051 (The Pile)

Max Activating Token Index: 941

Text #12

Max Range: 3.1910. Min Range: -3.1910

Max Act: 2.3659. Min Act: -0.0000

Data Index: 1071698 (The Pile)

Max Activating Token Index: 109

Text #13

Max Range: 3.1910. Min Range: -3.1910

Max Act: 2.4356. Min Act: 0.0000

Data Index: 572393 (The Pile)

Max Activating Token Index: 951

Text #14

Max Range: 3.1910. Min Range: -3.1910

Max Act: 2.6022. Min Act: 0.0000

Data Index: 303775 (The Pile)

Max Activating Token Index: 459

Text #15

Max Range: 3.1910. Min Range: -3.1910

Max Act: 2.5766. Min Act: -0.0000

Data Index: 232143 (The Pile)

Max Activating Token Index: 365

Text #16

Max Range: 3.1910. Min Range: -3.1910

Max Act: 2.5715. Min Act: 0.0001

Data Index: 1296629 (The Pile)

Max Activating Token Index: 1002

Text #17

Max Range: 3.1910. Min Range: -3.1910

Max Act: 2.4217. Min Act: 0.0000

Data Index: 512891 (The Pile)

Max Activating Token Index: 440

Text #18

Max Range: 3.1910. Min Range: -3.1910

Max Act: 2.5336. Min Act: -0.0000

Data Index: 440339 (The Pile)

Max Activating Token Index: 308

Text #19

Max Range: 3.1910. Min Range: -3.1910

Max Act: 2.5274. Min Act: 0.0001

Data Index: 1373426 (The Pile)

Max Activating Token Index: 327