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

Dataset: The Pile

Neuron 3404 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.4148. Min Act: -0.0000

Data Index: 752010 (The Pile)

Max Activating Token Index: 185

Text #1

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.4057. Min Act: -0.0000

Data Index: 340443 (The Pile)

Max Activating Token Index: 60

Text #2

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.4884. Min Act: -0.0000

Data Index: 1344338 (The Pile)

Max Activating Token Index: 141

Text #3

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.4258. Min Act: -0.0000

Data Index: 147382 (The Pile)

Max Activating Token Index: 783

Text #4

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.3012. Min Act: -0.0000

Data Index: 536314 (The Pile)

Max Activating Token Index: 244

Text #5

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.1865. Min Act: -0.0000

Data Index: 1587925 (The Pile)

Max Activating Token Index: 805

Text #6

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.1957. Min Act: -0.0000

Data Index: 1836330 (The Pile)

Max Activating Token Index: 846

Text #7

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.0850. Min Act: -0.0000

Data Index: 1912415 (The Pile)

Max Activating Token Index: 1002

Text #8

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.1597. Min Act: -0.0000

Data Index: 69301 (The Pile)

Max Activating Token Index: 257

Text #9

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.1012. Min Act: -0.0000

Data Index: 555464 (The Pile)

Max Activating Token Index: 353

Text #10

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.1650. Min Act: -0.0000

Data Index: 1163314 (The Pile)

Max Activating Token Index: 865

Text #11

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.0858. Min Act: -0.0000

Data Index: 478866 (The Pile)

Max Activating Token Index: 836

Text #12

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.0436. Min Act: -0.0000

Data Index: 554080 (The Pile)

Max Activating Token Index: 924

Text #13

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.1080. Min Act: -0.0000

Data Index: 1963865 (The Pile)

Max Activating Token Index: 277

Text #14

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.1378. Min Act: -0.0000

Data Index: 992448 (The Pile)

Max Activating Token Index: 404

Text #15

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.0052. Min Act: -0.0000

Data Index: 392955 (The Pile)

Max Activating Token Index: 97

Text #16

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.0613. Min Act: -0.0000

Data Index: 468656 (The Pile)

Max Activating Token Index: 860

Text #17

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.1027. Min Act: -0.0000

Data Index: 1081299 (The Pile)

Max Activating Token Index: 197

Text #18

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.0259. Min Act: -0.0000

Data Index: 496671 (The Pile)

Max Activating Token Index: 205

Text #19

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.0335. Min Act: -0.0000

Data Index: 1458862 (The Pile)

Max Activating Token Index: 164