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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3818 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.3144. Min Act: -0.0001

Data Index: 631575 (C4 (Web Text))

Max Activating Token Index: 521

Text #1

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2242. Min Act: -0.0001

Data Index: 754238 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2255. Min Act: -0.0001

Data Index: 669707 (C4 (Web Text))

Max Activating Token Index: 931

Text #3

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2155. Min Act: -0.0000

Data Index: 1205773 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2058. Min Act: -0.0001

Data Index: 657848 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2067. Min Act: -0.0000

Data Index: 760690 (C4 (Web Text))

Max Activating Token Index: 830

Text #6

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1905. Min Act: -0.0000

Data Index: 1234387 (C4 (Web Text))

Max Activating Token Index: 881

Text #7

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2138. Min Act: -0.0001

Data Index: 531930 (C4 (Web Text))

Max Activating Token Index: 507

Text #8

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2016. Min Act: -0.0001

Data Index: 878463 (C4 (Web Text))

Max Activating Token Index: 504

Text #9

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1976. Min Act: -0.0001

Data Index: 105267 (C4 (Web Text))

Max Activating Token Index: 853

Text #10

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2206. Min Act: -0.0000

Data Index: 626451 (C4 (Web Text))

Max Activating Token Index: 790

Text #11

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2095. Min Act: -0.0001

Data Index: 924403 (C4 (Web Text))

Max Activating Token Index: 493

Text #12

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1733. Min Act: -0.0001

Data Index: 378954 (C4 (Web Text))

Max Activating Token Index: 817

Text #13

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1853. Min Act: -0.0001

Data Index: 557066 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1780. Min Act: -0.0000

Data Index: 923533 (C4 (Web Text))

Max Activating Token Index: 12

Text #15

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1854. Min Act: -0.0001

Data Index: 624331 (C4 (Web Text))

Max Activating Token Index: 266

Text #16

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1717. Min Act: -0.0000

Data Index: 26833 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1654. Min Act: -0.0001

Data Index: 684906 (C4 (Web Text))

Max Activating Token Index: 166

Text #18

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1751. Min Act: -0.0000

Data Index: 146925 (C4 (Web Text))

Max Activating Token Index: 844

Text #19

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1668. Min Act: -0.0000

Data Index: 1311379 (C4 (Web Text))

Max Activating Token Index: 1022