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

Dataset: The Pile

Neuron 4080 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: 0.6861. Min Range: -0.6861

Max Act: 0.6861. Min Act: -0.0000

Data Index: 600960 (The Pile)

Max Activating Token Index: 532

Text #1

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.6006. Min Act: -0.0000

Data Index: 1663508 (The Pile)

Max Activating Token Index: 766

Text #2

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.5876. Min Act: -0.0000

Data Index: 1850290 (The Pile)

Max Activating Token Index: 347

Text #3

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.5749. Min Act: -0.0000

Data Index: 1282065 (The Pile)

Max Activating Token Index: 38

Text #4

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.5951. Min Act: -0.0000

Data Index: 1850841 (The Pile)

Max Activating Token Index: 656

Text #5

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.5414. Min Act: -0.0000

Data Index: 1901462 (The Pile)

Max Activating Token Index: 538

Text #6

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.5605. Min Act: -0.0000

Data Index: 1608491 (The Pile)

Max Activating Token Index: 34

Text #7

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.5397. Min Act: -0.0000

Data Index: 287957 (The Pile)

Max Activating Token Index: 642

Text #8

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.5319. Min Act: -0.0000

Data Index: 1952658 (The Pile)

Max Activating Token Index: 842

Text #9

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.5654. Min Act: -0.0000

Data Index: 1670136 (The Pile)

Max Activating Token Index: 7

Text #10

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.5216. Min Act: -0.0000

Data Index: 426432 (The Pile)

Max Activating Token Index: 847

Text #11

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.5383. Min Act: -0.0000

Data Index: 1935733 (The Pile)

Max Activating Token Index: 42

Text #12

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.5027. Min Act: -0.0000

Data Index: 1857860 (The Pile)

Max Activating Token Index: 770

Text #13

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.5197. Min Act: -0.0000

Data Index: 1172776 (The Pile)

Max Activating Token Index: 857

Text #14

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.5145. Min Act: -0.0000

Data Index: 196414 (The Pile)

Max Activating Token Index: 4

Text #15

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.4890. Min Act: -0.0000

Data Index: 1179421 (The Pile)

Max Activating Token Index: 340

Text #16

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.5270. Min Act: -0.0000

Data Index: 1057348 (The Pile)

Max Activating Token Index: 601

Text #17

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.5137. Min Act: -0.0000

Data Index: 568871 (The Pile)

Max Activating Token Index: 1018

Text #18

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.5173. Min Act: -0.0000

Data Index: 1951109 (The Pile)

Max Activating Token Index: 1004

Text #19

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.4867. Min Act: -0.0000

Data Index: 916266 (The Pile)

Max Activating Token Index: 160