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

Dataset: The Pile

Neuron 1819 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: 1.0136. Min Range: -1.0136

Max Act: 1.0136. Min Act: -0.0000

Data Index: 1876561 (The Pile)

Max Activating Token Index: 325

Text #1

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.9299. Min Act: -0.0000

Data Index: 176812 (The Pile)

Max Activating Token Index: 86

Text #2

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.9042. Min Act: -0.0000

Data Index: 640751 (The Pile)

Max Activating Token Index: 869

Text #3

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.9732. Min Act: -0.0000

Data Index: 433850 (The Pile)

Max Activating Token Index: 121

Text #4

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.9853. Min Act: -0.0000

Data Index: 1051873 (The Pile)

Max Activating Token Index: 716

Text #5

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.9232. Min Act: -0.0000

Data Index: 1758756 (The Pile)

Max Activating Token Index: 377

Text #6

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.9310. Min Act: -0.0000

Data Index: 922123 (The Pile)

Max Activating Token Index: 299

Text #7

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.8636. Min Act: -0.0000

Data Index: 398930 (The Pile)

Max Activating Token Index: 99

Text #8

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.9170. Min Act: -0.0000

Data Index: 454461 (The Pile)

Max Activating Token Index: 378

Text #9

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.8867. Min Act: -0.0000

Data Index: 1582794 (The Pile)

Max Activating Token Index: 72

Text #10

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.8967. Min Act: -0.0000

Data Index: 1094247 (The Pile)

Max Activating Token Index: 653

Text #11

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.8710. Min Act: -0.0000

Data Index: 917374 (The Pile)

Max Activating Token Index: 325

Text #12

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.8432. Min Act: -0.0000

Data Index: 936789 (The Pile)

Max Activating Token Index: 473

Text #13

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.8123. Min Act: -0.0000

Data Index: 889294 (The Pile)

Max Activating Token Index: 66

Text #14

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.7977. Min Act: -0.0000

Data Index: 231629 (The Pile)

Max Activating Token Index: 75

Text #15

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.8107. Min Act: -0.0000

Data Index: 822058 (The Pile)

Max Activating Token Index: 432

Text #16

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.8324. Min Act: -0.0000

Data Index: 1643130 (The Pile)

Max Activating Token Index: 78

Text #17

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.7580. Min Act: -0.0000

Data Index: 1554844 (The Pile)

Max Activating Token Index: 179

Text #18

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.8086. Min Act: -0.0000

Data Index: 1644069 (The Pile)

Max Activating Token Index: 103

Text #19

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.7346. Min Act: -0.0000

Data Index: 266794 (The Pile)

Max Activating Token Index: 99