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

Dataset: The Pile

Neuron 3961 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.4227. Min Act: -0.0000

Data Index: 452104 (The Pile)

Max Activating Token Index: 188

Text #1

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.4125. Min Act: -0.0000

Data Index: 562153 (The Pile)

Max Activating Token Index: 316

Text #2

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.3662. Min Act: -0.0000

Data Index: 1999395 (The Pile)

Max Activating Token Index: 20

Text #3

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.4117. Min Act: -0.0000

Data Index: 51350 (The Pile)

Max Activating Token Index: 942

Text #4

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.3725. Min Act: -0.0000

Data Index: 243724 (The Pile)

Max Activating Token Index: 55

Text #5

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.3558. Min Act: -0.0000

Data Index: 624366 (The Pile)

Max Activating Token Index: 645

Text #6

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.3306. Min Act: -0.0000

Data Index: 46676 (The Pile)

Max Activating Token Index: 37

Text #7

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.3519. Min Act: -0.0000

Data Index: 1899038 (The Pile)

Max Activating Token Index: 993

Text #8

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.3434. Min Act: -0.0000

Data Index: 1809410 (The Pile)

Max Activating Token Index: 811

Text #9

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.3318. Min Act: -0.0000

Data Index: 295156 (The Pile)

Max Activating Token Index: 16

Text #10

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.3289. Min Act: -0.0000

Data Index: 512502 (The Pile)

Max Activating Token Index: 22

Text #11

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.3077. Min Act: -0.0000

Data Index: 202765 (The Pile)

Max Activating Token Index: 37

Text #12

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.3046. Min Act: -0.0000

Data Index: 900915 (The Pile)

Max Activating Token Index: 98

Text #13

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.3107. Min Act: -0.0000

Data Index: 348777 (The Pile)

Max Activating Token Index: 137

Text #14

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.2982. Min Act: -0.0000

Data Index: 820048 (The Pile)

Max Activating Token Index: 837

Text #15

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.3167. Min Act: -0.0000

Data Index: 1504346 (The Pile)

Max Activating Token Index: 140

Text #16

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.3101. Min Act: -0.0000

Data Index: 1278636 (The Pile)

Max Activating Token Index: 774

Text #17

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.3401. Min Act: -0.0000

Data Index: 1110361 (The Pile)

Max Activating Token Index: 754

Text #18

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.3772. Min Act: -0.0000

Data Index: 1735836 (The Pile)

Max Activating Token Index: 780

Text #19

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.3069. Min Act: -0.0000

Data Index: 467819 (The Pile)

Max Activating Token Index: 945