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

Dataset: The Pile

Neuron 436 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: 1.7101. Min Range: -1.7101

Max Act: 1.7101. Min Act: -0.0000

Data Index: 916865 (The Pile)

Max Activating Token Index: 678

Text #1

Max Range: 1.7101. Min Range: -1.7101

Max Act: 1.4816. Min Act: -0.0000

Data Index: 1741070 (The Pile)

Max Activating Token Index: 173

Text #2

Max Range: 1.7101. Min Range: -1.7101

Max Act: 1.5507. Min Act: -0.0000

Data Index: 1266662 (The Pile)

Max Activating Token Index: 189

Text #3

Max Range: 1.7101. Min Range: -1.7101

Max Act: 1.6015. Min Act: -0.0000

Data Index: 470702 (The Pile)

Max Activating Token Index: 106

Text #4

Max Range: 1.7101. Min Range: -1.7101

Max Act: 1.4078. Min Act: -0.0000

Data Index: 55790 (The Pile)

Max Activating Token Index: 604

Text #5

Max Range: 1.7101. Min Range: -1.7101

Max Act: 1.3179. Min Act: -0.0000

Data Index: 1381049 (The Pile)

Max Activating Token Index: 558

Text #6

Max Range: 1.7101. Min Range: -1.7101

Max Act: 1.2281. Min Act: -0.0000

Data Index: 403722 (The Pile)

Max Activating Token Index: 220

Text #7

Max Range: 1.7101. Min Range: -1.7101

Max Act: 1.2459. Min Act: -0.0000

Data Index: 1855916 (The Pile)

Max Activating Token Index: 575

Text #8

Max Range: 1.7101. Min Range: -1.7101

Max Act: 1.1261. Min Act: -0.0000

Data Index: 1056430 (The Pile)

Max Activating Token Index: 1012

Text #9

Max Range: 1.7101. Min Range: -1.7101

Max Act: 1.2622. Min Act: -0.0000

Data Index: 707933 (The Pile)

Max Activating Token Index: 34

Text #10

Max Range: 1.7101. Min Range: -1.7101

Max Act: 1.1499. Min Act: -0.0000

Data Index: 1277176 (The Pile)

Max Activating Token Index: 516

Text #11

Max Range: 1.7101. Min Range: -1.7101

Max Act: 1.2596. Min Act: -0.0000

Data Index: 45350 (The Pile)

Max Activating Token Index: 148

Text #12

Max Range: 1.7101. Min Range: -1.7101

Max Act: 1.1874. Min Act: -0.0000

Data Index: 1525531 (The Pile)

Max Activating Token Index: 430

Text #13

Max Range: 1.7101. Min Range: -1.7101

Max Act: 0.9861. Min Act: -0.0000

Data Index: 1929711 (The Pile)

Max Activating Token Index: 130

Text #14

Max Range: 1.7101. Min Range: -1.7101

Max Act: 1.3242. Min Act: -0.0000

Data Index: 169462 (The Pile)

Max Activating Token Index: 638

Text #15

Max Range: 1.7101. Min Range: -1.7101

Max Act: 1.1709. Min Act: -0.0000

Data Index: 274352 (The Pile)

Max Activating Token Index: 576

Text #16

Max Range: 1.7101. Min Range: -1.7101

Max Act: 1.1329. Min Act: -0.0000

Data Index: 49322 (The Pile)

Max Activating Token Index: 529

Text #17

Max Range: 1.7101. Min Range: -1.7101

Max Act: 1.2218. Min Act: -0.0000

Data Index: 1122795 (The Pile)

Max Activating Token Index: 864

Text #18

Max Range: 1.7101. Min Range: -1.7101

Max Act: 1.1123. Min Act: -0.0000

Data Index: 1975179 (The Pile)

Max Activating Token Index: 811

Text #19

Max Range: 1.7101. Min Range: -1.7101

Max Act: 1.0329. Min Act: -0.0000

Data Index: 680664 (The Pile)

Max Activating Token Index: 785