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

Dataset: The Pile

Neuron 3522 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: 0.9145. Min Range: -0.9145

Max Act: 0.9145. Min Act: -0.0000

Data Index: 326171 (The Pile)

Max Activating Token Index: 259

Text #1

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.8925. Min Act: -0.0000

Data Index: 1953222 (The Pile)

Max Activating Token Index: 102

Text #2

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7160. Min Act: -0.0000

Data Index: 142158 (The Pile)

Max Activating Token Index: 737

Text #3

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7628. Min Act: -0.0000

Data Index: 807808 (The Pile)

Max Activating Token Index: 308

Text #4

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.8524. Min Act: -0.0000

Data Index: 1259805 (The Pile)

Max Activating Token Index: 635

Text #5

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.8442. Min Act: -0.0000

Data Index: 843070 (The Pile)

Max Activating Token Index: 518

Text #6

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7686. Min Act: -0.0000

Data Index: 1237459 (The Pile)

Max Activating Token Index: 100

Text #7

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7632. Min Act: -0.0000

Data Index: 13643 (The Pile)

Max Activating Token Index: 324

Text #8

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.6593. Min Act: -0.0000

Data Index: 122041 (The Pile)

Max Activating Token Index: 967

Text #9

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7234. Min Act: -0.0000

Data Index: 194931 (The Pile)

Max Activating Token Index: 564

Text #10

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7519. Min Act: -0.0000

Data Index: 262208 (The Pile)

Max Activating Token Index: 949

Text #11

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.6293. Min Act: -0.0000

Data Index: 1111593 (The Pile)

Max Activating Token Index: 710

Text #12

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.6039. Min Act: -0.0000

Data Index: 427241 (The Pile)

Max Activating Token Index: 814

Text #13

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7432. Min Act: -0.0000

Data Index: 961945 (The Pile)

Max Activating Token Index: 276

Text #14

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7164. Min Act: -0.0000

Data Index: 43077 (The Pile)

Max Activating Token Index: 68

Text #15

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7010. Min Act: -0.0000

Data Index: 1462464 (The Pile)

Max Activating Token Index: 213

Text #16

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7010. Min Act: -0.0000

Data Index: 712353 (The Pile)

Max Activating Token Index: 744

Text #17

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.6794. Min Act: -0.0000

Data Index: 1340502 (The Pile)

Max Activating Token Index: 21

Text #18

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7620. Min Act: -0.0000

Data Index: 1308631 (The Pile)

Max Activating Token Index: 166

Text #19

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7018. Min Act: -0.0000

Data Index: 1418874 (The Pile)

Max Activating Token Index: 385