Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 1997 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.3171. Min Act: -0.0000

Data Index: 1499564 (The Pile)

Max Activating Token Index: 786

Text #1

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.3251. Min Act: -0.0001

Data Index: 427218 (The Pile)

Max Activating Token Index: 402

Text #2

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.3088. Min Act: -0.0000

Data Index: 1534124 (The Pile)

Max Activating Token Index: 736

Text #3

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2788. Min Act: -0.0000

Data Index: 1927979 (The Pile)

Max Activating Token Index: 467

Text #4

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2706. Min Act: -0.0001

Data Index: 798186 (The Pile)

Max Activating Token Index: 855

Text #5

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2388. Min Act: -0.0001

Data Index: 1340033 (The Pile)

Max Activating Token Index: 391

Text #6

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2456. Min Act: -0.0001

Data Index: 1727518 (The Pile)

Max Activating Token Index: 978

Text #7

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2549. Min Act: -0.0000

Data Index: 1937440 (The Pile)

Max Activating Token Index: 178

Text #8

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2381. Min Act: -0.0000

Data Index: 1928770 (The Pile)

Max Activating Token Index: 945

Text #9

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2262. Min Act: -0.0000

Data Index: 422123 (The Pile)

Max Activating Token Index: 482

Text #10

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2536. Min Act: -0.0000

Data Index: 1020491 (The Pile)

Max Activating Token Index: 1012

Text #11

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2113. Min Act: -0.0001

Data Index: 1677190 (The Pile)

Max Activating Token Index: 292

Text #12

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2186. Min Act: -0.0000

Data Index: 118027 (The Pile)

Max Activating Token Index: 549

Text #13

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2153. Min Act: -0.0000

Data Index: 202195 (The Pile)

Max Activating Token Index: 189

Text #14

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2226. Min Act: -0.0000

Data Index: 1560585 (The Pile)

Max Activating Token Index: 797

Text #15

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2014. Min Act: -0.0000

Data Index: 1133054 (The Pile)

Max Activating Token Index: 580

Text #16

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2072. Min Act: -0.0000

Data Index: 742871 (The Pile)

Max Activating Token Index: 560

Text #17

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.1987. Min Act: -0.0001

Data Index: 48736 (The Pile)

Max Activating Token Index: 27

Text #18

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.1981. Min Act: -0.0000

Data Index: 1284006 (The Pile)

Max Activating Token Index: 711

Text #19

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.1978. Min Act: -0.0000

Data Index: 1790802 (The Pile)

Max Activating Token Index: 538