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

Dataset: The Pile

Neuron 2340 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.9167. Min Act: -0.0000

Data Index: 1958101 (The Pile)

Max Activating Token Index: 590

Text #1

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.9030. Min Act: -0.0000

Data Index: 1388983 (The Pile)

Max Activating Token Index: 621

Text #2

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.8643. Min Act: -0.0000

Data Index: 1481226 (The Pile)

Max Activating Token Index: 787

Text #3

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.8490. Min Act: -0.0000

Data Index: 10242 (The Pile)

Max Activating Token Index: 302

Text #4

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.8401. Min Act: -0.0000

Data Index: 1243119 (The Pile)

Max Activating Token Index: 680

Text #5

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.7626. Min Act: -0.0000

Data Index: 573786 (The Pile)

Max Activating Token Index: 830

Text #6

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.8461. Min Act: -0.0000

Data Index: 160149 (The Pile)

Max Activating Token Index: 956

Text #7

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.8854. Min Act: -0.0000

Data Index: 1818174 (The Pile)

Max Activating Token Index: 1012

Text #8

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.8266. Min Act: -0.0000

Data Index: 320825 (The Pile)

Max Activating Token Index: 940

Text #9

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.7620. Min Act: -0.0000

Data Index: 110658 (The Pile)

Max Activating Token Index: 816

Text #10

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.8718. Min Act: -0.0000

Data Index: 1749116 (The Pile)

Max Activating Token Index: 745

Text #11

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.7846. Min Act: -0.0000

Data Index: 1228797 (The Pile)

Max Activating Token Index: 610

Text #12

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.7891. Min Act: -0.0000

Data Index: 746283 (The Pile)

Max Activating Token Index: 243

Text #13

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.7709. Min Act: -0.0000

Data Index: 307522 (The Pile)

Max Activating Token Index: 829

Text #14

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.7429. Min Act: -0.0000

Data Index: 1809017 (The Pile)

Max Activating Token Index: 630

Text #15

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.8023. Min Act: -0.0000

Data Index: 1860264 (The Pile)

Max Activating Token Index: 575

Text #16

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.7044. Min Act: -0.0000

Data Index: 1251681 (The Pile)

Max Activating Token Index: 31

Text #17

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.8359. Min Act: 0.0000

Data Index: 1028401 (The Pile)

Max Activating Token Index: 772

Text #18

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.7039. Min Act: -0.0000

Data Index: 44163 (The Pile)

Max Activating Token Index: 1000

Text #19

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.7283. Min Act: -0.0000

Data Index: 1568082 (The Pile)

Max Activating Token Index: 575