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

Dataset: The Pile

Neuron 3488 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2866. Min Act: -0.0000

Data Index: 161484 (The Pile)

Max Activating Token Index: 597

Text #1

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2842. Min Act: 0.0000

Data Index: 1983600 (The Pile)

Max Activating Token Index: 373

Text #2

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2430. Min Act: -0.0000

Data Index: 1166103 (The Pile)

Max Activating Token Index: 574

Text #3

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2358. Min Act: -0.0000

Data Index: 1114562 (The Pile)

Max Activating Token Index: 881

Text #4

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2447. Min Act: -0.0000

Data Index: 108119 (The Pile)

Max Activating Token Index: 625

Text #5

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2258. Min Act: -0.0000

Data Index: 1957939 (The Pile)

Max Activating Token Index: 93

Text #6

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2291. Min Act: 0.0000

Data Index: 322715 (The Pile)

Max Activating Token Index: 880

Text #7

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2390. Min Act: -0.0000

Data Index: 1611619 (The Pile)

Max Activating Token Index: 618

Text #8

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2266. Min Act: -0.0000

Data Index: 452644 (The Pile)

Max Activating Token Index: 844

Text #9

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2333. Min Act: -0.0000

Data Index: 705310 (The Pile)

Max Activating Token Index: 823

Text #10

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2364. Min Act: -0.0000

Data Index: 1987646 (The Pile)

Max Activating Token Index: 471

Text #11

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2217. Min Act: -0.0000

Data Index: 1853318 (The Pile)

Max Activating Token Index: 133

Text #12

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2292. Min Act: -0.0000

Data Index: 774790 (The Pile)

Max Activating Token Index: 917

Text #13

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2245. Min Act: -0.0000

Data Index: 1229655 (The Pile)

Max Activating Token Index: 798

Text #14

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2142. Min Act: -0.0000

Data Index: 459002 (The Pile)

Max Activating Token Index: 598

Text #15

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2163. Min Act: -0.0000

Data Index: 263143 (The Pile)

Max Activating Token Index: 193

Text #16

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2031. Min Act: 0.0000

Data Index: 1626699 (The Pile)

Max Activating Token Index: 745

Text #17

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2166. Min Act: -0.0000

Data Index: 1692198 (The Pile)

Max Activating Token Index: 204

Text #18

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2075. Min Act: -0.0000

Data Index: 1739571 (The Pile)

Max Activating Token Index: 778

Text #19

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2125. Min Act: -0.0000

Data Index: 1758860 (The Pile)

Max Activating Token Index: 533