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

Dataset: The Pile

Neuron 1826 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.5428. Min Act: -0.0000

Data Index: 779215 (The Pile)

Max Activating Token Index: 823

Text #1

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4930. Min Act: -0.0000

Data Index: 927987 (The Pile)

Max Activating Token Index: 473

Text #2

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4579. Min Act: -0.0000

Data Index: 1111799 (The Pile)

Max Activating Token Index: 403

Text #3

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4418. Min Act: -0.0000

Data Index: 83104 (The Pile)

Max Activating Token Index: 980

Text #4

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4498. Min Act: -0.0000

Data Index: 510602 (The Pile)

Max Activating Token Index: 449

Text #5

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4574. Min Act: -0.0000

Data Index: 504764 (The Pile)

Max Activating Token Index: 871

Text #6

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4167. Min Act: -0.0000

Data Index: 616544 (The Pile)

Max Activating Token Index: 86

Text #7

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4105. Min Act: -0.0000

Data Index: 1069149 (The Pile)

Max Activating Token Index: 94

Text #8

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4326. Min Act: -0.0000

Data Index: 245184 (The Pile)

Max Activating Token Index: 286

Text #9

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4187. Min Act: -0.0000

Data Index: 1243924 (The Pile)

Max Activating Token Index: 413

Text #10

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4290. Min Act: -0.0000

Data Index: 297102 (The Pile)

Max Activating Token Index: 347

Text #11

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3993. Min Act: -0.0000

Data Index: 1234257 (The Pile)

Max Activating Token Index: 26

Text #12

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4230. Min Act: -0.0000

Data Index: 326106 (The Pile)

Max Activating Token Index: 109

Text #13

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4079. Min Act: -0.0000

Data Index: 286249 (The Pile)

Max Activating Token Index: 372

Text #14

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4194. Min Act: -0.0000

Data Index: 295872 (The Pile)

Max Activating Token Index: 730

Text #15

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4027. Min Act: -0.0000

Data Index: 1230970 (The Pile)

Max Activating Token Index: 123

Text #16

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4006. Min Act: -0.0000

Data Index: 1398271 (The Pile)

Max Activating Token Index: 44

Text #17

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3966. Min Act: -0.0000

Data Index: 1571374 (The Pile)

Max Activating Token Index: 288

Text #18

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4134. Min Act: -0.0000

Data Index: 1525668 (The Pile)

Max Activating Token Index: 21

Text #19

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4062. Min Act: -0.0000

Data Index: 1350607 (The Pile)

Max Activating Token Index: 637