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

Dataset: The Pile

Neuron 3099 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9218. Min Range: -0.9218

Max Act: 0.8734. Min Act: -0.0000

Data Index: 39254 (The Pile)

Max Activating Token Index: 356

Text #1

Max Range: 0.9218. Min Range: -0.9218

Max Act: 0.9094. Min Act: -0.0000

Data Index: 1731983 (The Pile)

Max Activating Token Index: 639

Text #2

Max Range: 0.9218. Min Range: -0.9218

Max Act: 0.7918. Min Act: -0.0000

Data Index: 124692 (The Pile)

Max Activating Token Index: 739

Text #3

Max Range: 0.9218. Min Range: -0.9218

Max Act: 0.8592. Min Act: -0.0000

Data Index: 154809 (The Pile)

Max Activating Token Index: 828

Text #4

Max Range: 0.9218. Min Range: -0.9218

Max Act: 0.8547. Min Act: -0.0000

Data Index: 825134 (The Pile)

Max Activating Token Index: 795

Text #5

Max Range: 0.9218. Min Range: -0.9218

Max Act: 0.8238. Min Act: -0.0000

Data Index: 591943 (The Pile)

Max Activating Token Index: 745

Text #6

Max Range: 0.9218. Min Range: -0.9218

Max Act: 0.8215. Min Act: -0.0000

Data Index: 512921 (The Pile)

Max Activating Token Index: 309

Text #7

Max Range: 0.9218. Min Range: -0.9218

Max Act: 0.8177. Min Act: -0.0000

Data Index: 1275437 (The Pile)

Max Activating Token Index: 295

Text #8

Max Range: 0.9218. Min Range: -0.9218

Max Act: 0.9218. Min Act: -0.0000

Data Index: 1776303 (The Pile)

Max Activating Token Index: 882

Text #9

Max Range: 0.9218. Min Range: -0.9218

Max Act: 0.8279. Min Act: -0.0000

Data Index: 102682 (The Pile)

Max Activating Token Index: 305

Text #10

Max Range: 0.9218. Min Range: -0.9218

Max Act: 0.7392. Min Act: -0.0000

Data Index: 288572 (The Pile)

Max Activating Token Index: 686

Text #11

Max Range: 0.9218. Min Range: -0.9218

Max Act: 0.7533. Min Act: -0.0000

Data Index: 847492 (The Pile)

Max Activating Token Index: 867

Text #12

Max Range: 0.9218. Min Range: -0.9218

Max Act: 0.7203. Min Act: -0.0000

Data Index: 1551294 (The Pile)

Max Activating Token Index: 947

Text #13

Max Range: 0.9218. Min Range: -0.9218

Max Act: 0.7491. Min Act: -0.0000

Data Index: 190975 (The Pile)

Max Activating Token Index: 625

Text #14

Max Range: 0.9218. Min Range: -0.9218

Max Act: 0.6236. Min Act: -0.0000

Data Index: 19293 (The Pile)

Max Activating Token Index: 774

Text #15

Max Range: 0.9218. Min Range: -0.9218

Max Act: 0.6805. Min Act: -0.0000

Data Index: 1748022 (The Pile)

Max Activating Token Index: 895

Text #16

Max Range: 0.9218. Min Range: -0.9218

Max Act: 0.6145. Min Act: -0.0000

Data Index: 1335442 (The Pile)

Max Activating Token Index: 808

Text #17

Max Range: 0.9218. Min Range: -0.9218

Max Act: 0.6828. Min Act: -0.0000

Data Index: 712353 (The Pile)

Max Activating Token Index: 828

Text #18

Max Range: 0.9218. Min Range: -0.9218

Max Act: 0.6724. Min Act: -0.0000

Data Index: 1893831 (The Pile)

Max Activating Token Index: 161

Text #19

Max Range: 0.9218. Min Range: -0.9218

Max Act: 0.6727. Min Act: -0.0000

Data Index: 1102332 (The Pile)

Max Activating Token Index: 896