Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1271 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 7.7208. Min Range: -7.7208

Max Act: 7.7208. Min Act: -0.0000

Data Index: 1692765 (The Pile)

Max Activating Token Index: 747

Text #1

Max Range: 7.7208. Min Range: -7.7208

Max Act: 7.6727. Min Act: -0.0000

Data Index: 1131141 (The Pile)

Max Activating Token Index: 990

Text #2

Max Range: 7.7208. Min Range: -7.7208

Max Act: 7.4998. Min Act: -0.0000

Data Index: 1329808 (The Pile)

Max Activating Token Index: 496

Text #3

Max Range: 7.7208. Min Range: -7.7208

Max Act: 7.3136. Min Act: -0.0000

Data Index: 1498763 (The Pile)

Max Activating Token Index: 439

Text #4

Max Range: 7.7208. Min Range: -7.7208

Max Act: 7.2086. Min Act: -0.0000

Data Index: 1196170 (The Pile)

Max Activating Token Index: 691

Text #5

Max Range: 7.7208. Min Range: -7.7208

Max Act: 7.5660. Min Act: -0.0000

Data Index: 70111 (The Pile)

Max Activating Token Index: 953

Text #6

Max Range: 7.7208. Min Range: -7.7208

Max Act: 7.3556. Min Act: -0.0000

Data Index: 1711261 (The Pile)

Max Activating Token Index: 714

Text #7

Max Range: 7.7208. Min Range: -7.7208

Max Act: 6.9545. Min Act: -0.0000

Data Index: 279396 (The Pile)

Max Activating Token Index: 695

Text #8

Max Range: 7.7208. Min Range: -7.7208

Max Act: 6.5830. Min Act: -0.0000

Data Index: 147091 (The Pile)

Max Activating Token Index: 737

Text #9

Max Range: 7.7208. Min Range: -7.7208

Max Act: 7.1519. Min Act: -0.0000

Data Index: 188932 (The Pile)

Max Activating Token Index: 626

Text #10

Max Range: 7.7208. Min Range: -7.7208

Max Act: 6.9103. Min Act: -0.0000

Data Index: 1565014 (The Pile)

Max Activating Token Index: 374

Text #11

Max Range: 7.7208. Min Range: -7.7208

Max Act: 7.0675. Min Act: -0.0000

Data Index: 1381962 (The Pile)

Max Activating Token Index: 961

Text #12

Max Range: 7.7208. Min Range: -7.7208

Max Act: 7.0232. Min Act: -0.0000

Data Index: 421490 (The Pile)

Max Activating Token Index: 259

Text #13

Max Range: 7.7208. Min Range: -7.7208

Max Act: 7.1480. Min Act: -0.0000

Data Index: 469437 (The Pile)

Max Activating Token Index: 541

Text #14

Max Range: 7.7208. Min Range: -7.7208

Max Act: 6.3237. Min Act: -0.0000

Data Index: 678303 (The Pile)

Max Activating Token Index: 664

Text #15

Max Range: 7.7208. Min Range: -7.7208

Max Act: 6.6899. Min Act: -0.0000

Data Index: 938597 (The Pile)

Max Activating Token Index: 989

Text #16

Max Range: 7.7208. Min Range: -7.7208

Max Act: 6.5892. Min Act: -0.0000

Data Index: 660997 (The Pile)

Max Activating Token Index: 513

Text #17

Max Range: 7.7208. Min Range: -7.7208

Max Act: 6.4896. Min Act: -0.0000

Data Index: 1764699 (The Pile)

Max Activating Token Index: 774

Text #18

Max Range: 7.7208. Min Range: -7.7208

Max Act: 6.2356. Min Act: -0.0000

Data Index: 1035067 (The Pile)

Max Activating Token Index: 951

Text #19

Max Range: 7.7208. Min Range: -7.7208

Max Act: 6.3558. Min Act: -0.0000

Data Index: 1612816 (The Pile)

Max Activating Token Index: 953