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

Dataset: The Pile

Neuron 2761 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4442. Min Range: -1.4442

Max Act: 1.4442. Min Act: -0.0000

Data Index: 1040176 (The Pile)

Max Activating Token Index: 663

Text #1

Max Range: 1.4442. Min Range: -1.4442

Max Act: 1.4333. Min Act: -0.0000

Data Index: 310698 (The Pile)

Max Activating Token Index: 50

Text #2

Max Range: 1.4442. Min Range: -1.4442

Max Act: 1.3145. Min Act: -0.0000

Data Index: 453001 (The Pile)

Max Activating Token Index: 827

Text #3

Max Range: 1.4442. Min Range: -1.4442

Max Act: 1.3558. Min Act: -0.0000

Data Index: 470196 (The Pile)

Max Activating Token Index: 92

Text #4

Max Range: 1.4442. Min Range: -1.4442

Max Act: 1.2699. Min Act: -0.0000

Data Index: 1225046 (The Pile)

Max Activating Token Index: 27

Text #5

Max Range: 1.4442. Min Range: -1.4442

Max Act: 1.2884. Min Act: -0.0000

Data Index: 1410362 (The Pile)

Max Activating Token Index: 78

Text #6

Max Range: 1.4442. Min Range: -1.4442

Max Act: 1.1914. Min Act: -0.0000

Data Index: 22856 (The Pile)

Max Activating Token Index: 174

Text #7

Max Range: 1.4442. Min Range: -1.4442

Max Act: 1.2564. Min Act: -0.0000

Data Index: 1261172 (The Pile)

Max Activating Token Index: 30

Text #8

Max Range: 1.4442. Min Range: -1.4442

Max Act: 1.2202. Min Act: -0.0000

Data Index: 86973 (The Pile)

Max Activating Token Index: 43

Text #9

Max Range: 1.4442. Min Range: -1.4442

Max Act: 1.1023. Min Act: -0.0000

Data Index: 1825758 (The Pile)

Max Activating Token Index: 108

Text #10

Max Range: 1.4442. Min Range: -1.4442

Max Act: 1.1557. Min Act: -0.0000

Data Index: 1724653 (The Pile)

Max Activating Token Index: 45

Text #11

Max Range: 1.4442. Min Range: -1.4442

Max Act: 1.2288. Min Act: -0.0000

Data Index: 1992185 (The Pile)

Max Activating Token Index: 93

Text #12

Max Range: 1.4442. Min Range: -1.4442

Max Act: 1.1550. Min Act: -0.0000

Data Index: 1194015 (The Pile)

Max Activating Token Index: 181

Text #13

Max Range: 1.4442. Min Range: -1.4442

Max Act: 1.1876. Min Act: -0.0000

Data Index: 534272 (The Pile)

Max Activating Token Index: 253

Text #14

Max Range: 1.4442. Min Range: -1.4442

Max Act: 1.2007. Min Act: -0.0000

Data Index: 758857 (The Pile)

Max Activating Token Index: 175

Text #15

Max Range: 1.4442. Min Range: -1.4442

Max Act: 1.0807. Min Act: -0.0000

Data Index: 551852 (The Pile)

Max Activating Token Index: 112

Text #16

Max Range: 1.4442. Min Range: -1.4442

Max Act: 1.1723. Min Act: -0.0000

Data Index: 189853 (The Pile)

Max Activating Token Index: 119

Text #17

Max Range: 1.4442. Min Range: -1.4442

Max Act: 1.2153. Min Act: -0.0000

Data Index: 249226 (The Pile)

Max Activating Token Index: 229

Text #18

Max Range: 1.4442. Min Range: -1.4442

Max Act: 1.0979. Min Act: -0.0000

Data Index: 1010602 (The Pile)

Max Activating Token Index: 976

Text #19

Max Range: 1.4442. Min Range: -1.4442

Max Act: 1.1271. Min Act: -0.0000

Data Index: 1542629 (The Pile)

Max Activating Token Index: 63