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

Dataset: The Pile

Neuron 404 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: 1.2368. Min Range: -1.2368

Max Act: 1.2368. Min Act: -0.0000

Data Index: 788049 (The Pile)

Max Activating Token Index: 23

Text #1

Max Range: 1.2368. Min Range: -1.2368

Max Act: 1.0616. Min Act: -0.0000

Data Index: 52465 (The Pile)

Max Activating Token Index: 41

Text #2

Max Range: 1.2368. Min Range: -1.2368

Max Act: 0.8436. Min Act: -0.0000

Data Index: 4325 (The Pile)

Max Activating Token Index: 650

Text #3

Max Range: 1.2368. Min Range: -1.2368

Max Act: 0.9286. Min Act: -0.0000

Data Index: 842660 (The Pile)

Max Activating Token Index: 1000

Text #4

Max Range: 1.2368. Min Range: -1.2368

Max Act: 0.8688. Min Act: -0.0000

Data Index: 787331 (The Pile)

Max Activating Token Index: 202

Text #5

Max Range: 1.2368. Min Range: -1.2368

Max Act: 0.8319. Min Act: -0.0000

Data Index: 1221407 (The Pile)

Max Activating Token Index: 23

Text #6

Max Range: 1.2368. Min Range: -1.2368

Max Act: 1.0070. Min Act: -0.0000

Data Index: 1545099 (The Pile)

Max Activating Token Index: 719

Text #7

Max Range: 1.2368. Min Range: -1.2368

Max Act: 0.8492. Min Act: -0.0000

Data Index: 1701247 (The Pile)

Max Activating Token Index: 38

Text #8

Max Range: 1.2368. Min Range: -1.2368

Max Act: 0.7501. Min Act: -0.0000

Data Index: 998611 (The Pile)

Max Activating Token Index: 823

Text #9

Max Range: 1.2368. Min Range: -1.2368

Max Act: 0.8488. Min Act: -0.0000

Data Index: 1505080 (The Pile)

Max Activating Token Index: 570

Text #10

Max Range: 1.2368. Min Range: -1.2368

Max Act: 0.7173. Min Act: -0.0000

Data Index: 1590269 (The Pile)

Max Activating Token Index: 39

Text #11

Max Range: 1.2368. Min Range: -1.2368

Max Act: 0.8978. Min Act: -0.0000

Data Index: 923045 (The Pile)

Max Activating Token Index: 1009

Text #12

Max Range: 1.2368. Min Range: -1.2368

Max Act: 0.8522. Min Act: -0.0000

Data Index: 1769842 (The Pile)

Max Activating Token Index: 124

Text #13

Max Range: 1.2368. Min Range: -1.2368

Max Act: 0.7849. Min Act: -0.0000

Data Index: 265176 (The Pile)

Max Activating Token Index: 494

Text #14

Max Range: 1.2368. Min Range: -1.2368

Max Act: 0.8240. Min Act: -0.0000

Data Index: 1395609 (The Pile)

Max Activating Token Index: 271

Text #15

Max Range: 1.2368. Min Range: -1.2368

Max Act: 0.7224. Min Act: -0.0000

Data Index: 1016121 (The Pile)

Max Activating Token Index: 756

Text #16

Max Range: 1.2368. Min Range: -1.2368

Max Act: 0.7901. Min Act: -0.0000

Data Index: 388786 (The Pile)

Max Activating Token Index: 57

Text #17

Max Range: 1.2368. Min Range: -1.2368

Max Act: 0.8163. Min Act: -0.0000

Data Index: 1926390 (The Pile)

Max Activating Token Index: 862

Text #18

Max Range: 1.2368. Min Range: -1.2368

Max Act: 0.8575. Min Act: 0.0000

Data Index: 1399859 (The Pile)

Max Activating Token Index: 494

Text #19

Max Range: 1.2368. Min Range: -1.2368

Max Act: 0.7596. Min Act: -0.0000

Data Index: 1397927 (The Pile)

Max Activating Token Index: 594