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

Dataset: The Pile

Neuron 3763 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: 0.9216. Min Range: -0.9216

Max Act: 0.9216. Min Act: -0.0000

Data Index: 1105272 (The Pile)

Max Activating Token Index: 125

Text #1

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.8950. Min Act: -0.0000

Data Index: 454076 (The Pile)

Max Activating Token Index: 127

Text #2

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.8902. Min Act: -0.0000

Data Index: 1460815 (The Pile)

Max Activating Token Index: 946

Text #3

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.8368. Min Act: -0.0000

Data Index: 1318020 (The Pile)

Max Activating Token Index: 292

Text #4

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.8522. Min Act: -0.0000

Data Index: 1174216 (The Pile)

Max Activating Token Index: 199

Text #5

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7953. Min Act: 0.0001

Data Index: 1209066 (The Pile)

Max Activating Token Index: 318

Text #6

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.8119. Min Act: -0.0000

Data Index: 1176548 (The Pile)

Max Activating Token Index: 154

Text #7

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7811. Min Act: -0.0000

Data Index: 1212522 (The Pile)

Max Activating Token Index: 546

Text #8

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7536. Min Act: -0.0000

Data Index: 1558205 (The Pile)

Max Activating Token Index: 695

Text #9

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7645. Min Act: -0.0000

Data Index: 481674 (The Pile)

Max Activating Token Index: 481

Text #10

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.8125. Min Act: -0.0000

Data Index: 1291832 (The Pile)

Max Activating Token Index: 1014

Text #11

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7795. Min Act: -0.0000

Data Index: 1442714 (The Pile)

Max Activating Token Index: 28

Text #12

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7645. Min Act: 0.0000

Data Index: 1303020 (The Pile)

Max Activating Token Index: 560

Text #13

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7619. Min Act: -0.0000

Data Index: 1996879 (The Pile)

Max Activating Token Index: 221

Text #14

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7129. Min Act: -0.0000

Data Index: 743579 (The Pile)

Max Activating Token Index: 192

Text #15

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7278. Min Act: -0.0000

Data Index: 138758 (The Pile)

Max Activating Token Index: 110

Text #16

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.6673. Min Act: -0.0000

Data Index: 1015720 (The Pile)

Max Activating Token Index: 88

Text #17

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7051. Min Act: 0.0000

Data Index: 1593858 (The Pile)

Max Activating Token Index: 829

Text #18

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7259. Min Act: -0.0000

Data Index: 1574349 (The Pile)

Max Activating Token Index: 946

Text #19

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7189. Min Act: -0.0000

Data Index: 400987 (The Pile)

Max Activating Token Index: 988