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

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

Neuron 150 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1826. Min Range: -1.1826

Max Act: 1.1826. Min Act: -0.0000

Data Index: 49223 (C4 (Web Text))

Max Activating Token Index: 341

Text #1

Max Range: 1.1826. Min Range: -1.1826

Max Act: 1.0712. Min Act: -0.0000

Data Index: 35679 (C4 (Web Text))

Max Activating Token Index: 199

Text #2

Max Range: 1.1826. Min Range: -1.1826

Max Act: 1.0043. Min Act: -0.0000

Data Index: 1261844 (C4 (Web Text))

Max Activating Token Index: 503

Text #3

Max Range: 1.1826. Min Range: -1.1826

Max Act: 1.0738. Min Act: -0.0000

Data Index: 978803 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 1.1826. Min Range: -1.1826

Max Act: 1.0587. Min Act: -0.0000

Data Index: 1076223 (C4 (Web Text))

Max Activating Token Index: 77

Text #5

Max Range: 1.1826. Min Range: -1.1826

Max Act: 1.0143. Min Act: -0.0001

Data Index: 866421 (C4 (Web Text))

Max Activating Token Index: 259

Text #6

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.9811. Min Act: -0.0000

Data Index: 331284 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.9770. Min Act: -0.0001

Data Index: 1023492 (C4 (Web Text))

Max Activating Token Index: 284

Text #8

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.9669. Min Act: -0.0000

Data Index: 1270994 (C4 (Web Text))

Max Activating Token Index: 811

Text #9

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.9276. Min Act: -0.0000

Data Index: 76900 (C4 (Web Text))

Max Activating Token Index: 466

Text #10

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.9170. Min Act: -0.0000

Data Index: 1017038 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.9345. Min Act: -0.0001

Data Index: 735238 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.9312. Min Act: -0.0001

Data Index: 701275 (C4 (Web Text))

Max Activating Token Index: 974

Text #13

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.8928. Min Act: -0.0000

Data Index: 252155 (C4 (Web Text))

Max Activating Token Index: 752

Text #14

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.9074. Min Act: -0.0000

Data Index: 1190800 (C4 (Web Text))

Max Activating Token Index: 656

Text #15

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.8230. Min Act: -0.0000

Data Index: 304918 (C4 (Web Text))

Max Activating Token Index: 475

Text #16

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.9262. Min Act: -0.0000

Data Index: 1047465 (C4 (Web Text))

Max Activating Token Index: 415

Text #17

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.8714. Min Act: -0.0000

Data Index: 341631 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.8677. Min Act: -0.0000

Data Index: 809880 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.8414. Min Act: -0.0001

Data Index: 16425 (C4 (Web Text))

Max Activating Token Index: 84