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

Dataset: The Pile

Neuron 839 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.5207. Min Act: -0.0000

Data Index: 1966607 (The Pile)

Max Activating Token Index: 831

Text #1

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.4170. Min Act: -0.0000

Data Index: 1720427 (The Pile)

Max Activating Token Index: 327

Text #2

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.3272. Min Act: -0.0000

Data Index: 1996624 (The Pile)

Max Activating Token Index: 836

Text #3

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.1322. Min Act: -0.0000

Data Index: 1773024 (The Pile)

Max Activating Token Index: 153

Text #4

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.2499. Min Act: -0.0000

Data Index: 1662602 (The Pile)

Max Activating Token Index: 729

Text #5

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.3070. Min Act: -0.0000

Data Index: 21566 (The Pile)

Max Activating Token Index: 335

Text #6

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.2516. Min Act: -0.0000

Data Index: 1020728 (The Pile)

Max Activating Token Index: 860

Text #7

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.2076. Min Act: -0.0000

Data Index: 994456 (The Pile)

Max Activating Token Index: 822

Text #8

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.2420. Min Act: -0.0000

Data Index: 1005919 (The Pile)

Max Activating Token Index: 50

Text #9

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.1792. Min Act: -0.0000

Data Index: 1233174 (The Pile)

Max Activating Token Index: 358

Text #10

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.2106. Min Act: -0.0000

Data Index: 1509996 (The Pile)

Max Activating Token Index: 758

Text #11

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.0832. Min Act: -0.0000

Data Index: 525753 (The Pile)

Max Activating Token Index: 543

Text #12

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.1010. Min Act: -0.0000

Data Index: 727139 (The Pile)

Max Activating Token Index: 767

Text #13

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.1383. Min Act: -0.0000

Data Index: 622357 (The Pile)

Max Activating Token Index: 811

Text #14

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.0675. Min Act: -0.0000

Data Index: 1831654 (The Pile)

Max Activating Token Index: 82

Text #15

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.1958. Min Act: -0.0000

Data Index: 697262 (The Pile)

Max Activating Token Index: 317

Text #16

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.2010. Min Act: -0.0000

Data Index: 1434917 (The Pile)

Max Activating Token Index: 541

Text #17

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.1525. Min Act: -0.0000

Data Index: 1724502 (The Pile)

Max Activating Token Index: 836

Text #18

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.1269. Min Act: -0.0000

Data Index: 767341 (The Pile)

Max Activating Token Index: 92

Text #19

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.1465. Min Act: -0.0000

Data Index: 810096 (The Pile)

Max Activating Token Index: 560