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

Dataset: The Pile

Neuron 4045 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5364. Min Range: -1.5364

Max Act: 1.5364. Min Act: -0.0000

Data Index: 261285 (The Pile)

Max Activating Token Index: 117

Text #1

Max Range: 1.5364. Min Range: -1.5364

Max Act: 1.3887. Min Act: -0.0000

Data Index: 1402928 (The Pile)

Max Activating Token Index: 831

Text #2

Max Range: 1.5364. Min Range: -1.5364

Max Act: 1.4785. Min Act: -0.0000

Data Index: 631911 (The Pile)

Max Activating Token Index: 10

Text #3

Max Range: 1.5364. Min Range: -1.5364

Max Act: 1.3186. Min Act: -0.0000

Data Index: 1575473 (The Pile)

Max Activating Token Index: 349

Text #4

Max Range: 1.5364. Min Range: -1.5364

Max Act: 1.3155. Min Act: -0.0000

Data Index: 277365 (The Pile)

Max Activating Token Index: 858

Text #5

Max Range: 1.5364. Min Range: -1.5364

Max Act: 1.3468. Min Act: -0.0000

Data Index: 254264 (The Pile)

Max Activating Token Index: 111

Text #6

Max Range: 1.5364. Min Range: -1.5364

Max Act: 1.3388. Min Act: -0.0000

Data Index: 678131 (The Pile)

Max Activating Token Index: 125

Text #7

Max Range: 1.5364. Min Range: -1.5364

Max Act: 1.2408. Min Act: 0.0000

Data Index: 652703 (The Pile)

Max Activating Token Index: 15

Text #8

Max Range: 1.5364. Min Range: -1.5364

Max Act: 1.2801. Min Act: -0.0000

Data Index: 1019232 (The Pile)

Max Activating Token Index: 872

Text #9

Max Range: 1.5364. Min Range: -1.5364

Max Act: 1.2993. Min Act: -0.0000

Data Index: 1070284 (The Pile)

Max Activating Token Index: 56

Text #10

Max Range: 1.5364. Min Range: -1.5364

Max Act: 1.1757. Min Act: -0.0000

Data Index: 1792396 (The Pile)

Max Activating Token Index: 514

Text #11

Max Range: 1.5364. Min Range: -1.5364

Max Act: 1.3002. Min Act: -0.0000

Data Index: 1514056 (The Pile)

Max Activating Token Index: 32

Text #12

Max Range: 1.5364. Min Range: -1.5364

Max Act: 1.2116. Min Act: -0.0000

Data Index: 157826 (The Pile)

Max Activating Token Index: 848

Text #13

Max Range: 1.5364. Min Range: -1.5364

Max Act: 1.1880. Min Act: -0.0000

Data Index: 1805852 (The Pile)

Max Activating Token Index: 869

Text #14

Max Range: 1.5364. Min Range: -1.5364

Max Act: 1.1599. Min Act: -0.0000

Data Index: 1038014 (The Pile)

Max Activating Token Index: 22

Text #15

Max Range: 1.5364. Min Range: -1.5364

Max Act: 1.1988. Min Act: -0.0000

Data Index: 309998 (The Pile)

Max Activating Token Index: 603

Text #16

Max Range: 1.5364. Min Range: -1.5364

Max Act: 1.2716. Min Act: -0.0000

Data Index: 659218 (The Pile)

Max Activating Token Index: 8

Text #17

Max Range: 1.5364. Min Range: -1.5364

Max Act: 1.2487. Min Act: -0.0000

Data Index: 768889 (The Pile)

Max Activating Token Index: 55

Text #18

Max Range: 1.5364. Min Range: -1.5364

Max Act: 1.1751. Min Act: -0.0000

Data Index: 1369304 (The Pile)

Max Activating Token Index: 262

Text #19

Max Range: 1.5364. Min Range: -1.5364

Max Act: 1.1128. Min Act: -0.0000

Data Index: 778905 (The Pile)

Max Activating Token Index: 688