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

Dataset: The Pile

Neuron 474 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: 1.7057. Min Range: -1.7057

Max Act: 1.7057. Min Act: -0.0000

Data Index: 318885 (The Pile)

Max Activating Token Index: 420

Text #1

Max Range: 1.7057. Min Range: -1.7057

Max Act: 1.4180. Min Act: -0.0000

Data Index: 739823 (The Pile)

Max Activating Token Index: 589

Text #2

Max Range: 1.7057. Min Range: -1.7057

Max Act: 1.3838. Min Act: -0.0000

Data Index: 1488936 (The Pile)

Max Activating Token Index: 136

Text #3

Max Range: 1.7057. Min Range: -1.7057

Max Act: 1.2140. Min Act: -0.0000

Data Index: 1273384 (The Pile)

Max Activating Token Index: 247

Text #4

Max Range: 1.7057. Min Range: -1.7057

Max Act: 1.0853. Min Act: -0.0000

Data Index: 626924 (The Pile)

Max Activating Token Index: 147

Text #5

Max Range: 1.7057. Min Range: -1.7057

Max Act: 1.0520. Min Act: -0.0000

Data Index: 1283284 (The Pile)

Max Activating Token Index: 449

Text #6

Max Range: 1.7057. Min Range: -1.7057

Max Act: 1.1887. Min Act: -0.0000

Data Index: 1422 (The Pile)

Max Activating Token Index: 689

Text #7

Max Range: 1.7057. Min Range: -1.7057

Max Act: 1.0838. Min Act: -0.0000

Data Index: 1169550 (The Pile)

Max Activating Token Index: 631

Text #8

Max Range: 1.7057. Min Range: -1.7057

Max Act: 1.1039. Min Act: -0.0000

Data Index: 521058 (The Pile)

Max Activating Token Index: 269

Text #9

Max Range: 1.7057. Min Range: -1.7057

Max Act: 1.0859. Min Act: -0.0000

Data Index: 1853775 (The Pile)

Max Activating Token Index: 700

Text #10

Max Range: 1.7057. Min Range: -1.7057

Max Act: 1.0842. Min Act: -0.0000

Data Index: 169554 (The Pile)

Max Activating Token Index: 113

Text #11

Max Range: 1.7057. Min Range: -1.7057

Max Act: 1.1340. Min Act: -0.0000

Data Index: 128177 (The Pile)

Max Activating Token Index: 1016

Text #12

Max Range: 1.7057. Min Range: -1.7057

Max Act: 1.0931. Min Act: -0.0000

Data Index: 1959295 (The Pile)

Max Activating Token Index: 421

Text #13

Max Range: 1.7057. Min Range: -1.7057

Max Act: 1.0595. Min Act: -0.0000

Data Index: 1706207 (The Pile)

Max Activating Token Index: 191

Text #14

Max Range: 1.7057. Min Range: -1.7057

Max Act: 1.0113. Min Act: -0.0000

Data Index: 1535858 (The Pile)

Max Activating Token Index: 983

Text #15

Max Range: 1.7057. Min Range: -1.7057

Max Act: 1.0416. Min Act: -0.0000

Data Index: 786100 (The Pile)

Max Activating Token Index: 867

Text #16

Max Range: 1.7057. Min Range: -1.7057

Max Act: 1.1289. Min Act: -0.0000

Data Index: 298069 (The Pile)

Max Activating Token Index: 109

Text #17

Max Range: 1.7057. Min Range: -1.7057

Max Act: 1.0300. Min Act: 0.0000

Data Index: 1363108 (The Pile)

Max Activating Token Index: 59

Text #18

Max Range: 1.7057. Min Range: -1.7057

Max Act: 1.0554. Min Act: -0.0000

Data Index: 1966799 (The Pile)

Max Activating Token Index: 299

Text #19

Max Range: 1.7057. Min Range: -1.7057

Max Act: 1.0351. Min Act: -0.0000

Data Index: 879415 (The Pile)

Max Activating Token Index: 622