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

Dataset: The Pile

Neuron 1252 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: 1.3964. Min Range: -1.3964

Max Act: 1.3964. Min Act: -0.0000

Data Index: 1536075 (The Pile)

Max Activating Token Index: 13

Text #1

Max Range: 1.3964. Min Range: -1.3964

Max Act: 1.3421. Min Act: -0.0000

Data Index: 1576424 (The Pile)

Max Activating Token Index: 80

Text #2

Max Range: 1.3964. Min Range: -1.3964

Max Act: 1.2977. Min Act: -0.0000

Data Index: 1201058 (The Pile)

Max Activating Token Index: 129

Text #3

Max Range: 1.3964. Min Range: -1.3964

Max Act: 1.2281. Min Act: -0.0000

Data Index: 1120405 (The Pile)

Max Activating Token Index: 126

Text #4

Max Range: 1.3964. Min Range: -1.3964

Max Act: 1.1690. Min Act: -0.0000

Data Index: 316291 (The Pile)

Max Activating Token Index: 72

Text #5

Max Range: 1.3964. Min Range: -1.3964

Max Act: 0.9997. Min Act: -0.0000

Data Index: 1145653 (The Pile)

Max Activating Token Index: 70

Text #6

Max Range: 1.3964. Min Range: -1.3964

Max Act: 1.0230. Min Act: -0.0000

Data Index: 39372 (The Pile)

Max Activating Token Index: 44

Text #7

Max Range: 1.3964. Min Range: -1.3964

Max Act: 1.0620. Min Act: -0.0000

Data Index: 1106270 (The Pile)

Max Activating Token Index: 61

Text #8

Max Range: 1.3964. Min Range: -1.3964

Max Act: 1.0325. Min Act: -0.0000

Data Index: 697005 (The Pile)

Max Activating Token Index: 101

Text #9

Max Range: 1.3964. Min Range: -1.3964

Max Act: 0.9976. Min Act: -0.0000

Data Index: 1360737 (The Pile)

Max Activating Token Index: 99

Text #10

Max Range: 1.3964. Min Range: -1.3964

Max Act: 0.9910. Min Act: -0.0000

Data Index: 481389 (The Pile)

Max Activating Token Index: 350

Text #11

Max Range: 1.3964. Min Range: -1.3964

Max Act: 0.9486. Min Act: -0.0000

Data Index: 1272148 (The Pile)

Max Activating Token Index: 76

Text #12

Max Range: 1.3964. Min Range: -1.3964

Max Act: 1.0297. Min Act: -0.0000

Data Index: 1772144 (The Pile)

Max Activating Token Index: 161

Text #13

Max Range: 1.3964. Min Range: -1.3964

Max Act: 0.9168. Min Act: -0.0000

Data Index: 1922806 (The Pile)

Max Activating Token Index: 408

Text #14

Max Range: 1.3964. Min Range: -1.3964

Max Act: 0.9322. Min Act: -0.0000

Data Index: 591012 (The Pile)

Max Activating Token Index: 420

Text #15

Max Range: 1.3964. Min Range: -1.3964

Max Act: 0.9413. Min Act: -0.0000

Data Index: 416952 (The Pile)

Max Activating Token Index: 184

Text #16

Max Range: 1.3964. Min Range: -1.3964

Max Act: 0.9980. Min Act: -0.0000

Data Index: 428637 (The Pile)

Max Activating Token Index: 86

Text #17

Max Range: 1.3964. Min Range: -1.3964

Max Act: 0.8861. Min Act: -0.0000

Data Index: 40833 (The Pile)

Max Activating Token Index: 171

Text #18

Max Range: 1.3964. Min Range: -1.3964

Max Act: 0.9049. Min Act: -0.0000

Data Index: 497215 (The Pile)

Max Activating Token Index: 124

Text #19

Max Range: 1.3964. Min Range: -1.3964

Max Act: 0.9025. Min Act: -0.0000

Data Index: 392356 (The Pile)

Max Activating Token Index: 129