Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4534 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.8821. Min Act: 0.0000

Data Index: 440934 (C4 (Web Text))

Max Activating Token Index: 978

Text #1

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.8313. Min Act: 0.0000

Data Index: 3896 (C4 (Web Text))

Max Activating Token Index: 146

Text #2

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.8241. Min Act: 0.0000

Data Index: 106784 (C4 (Web Text))

Max Activating Token Index: 954

Text #3

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.7820. Min Act: -0.0000

Data Index: 941911 (C4 (Web Text))

Max Activating Token Index: 951

Text #4

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.7398. Min Act: 0.0000

Data Index: 174158 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.7322. Min Act: 0.0001

Data Index: 64712 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.7146. Min Act: 0.0000

Data Index: 869411 (C4 (Web Text))

Max Activating Token Index: 462

Text #7

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.7109. Min Act: 0.0001

Data Index: 746701 (C4 (Web Text))

Max Activating Token Index: 990

Text #8

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.6394. Min Act: 0.0000

Data Index: 165081 (C4 (Web Text))

Max Activating Token Index: 456

Text #9

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.5960. Min Act: -0.0000

Data Index: 238464 (C4 (Web Text))

Max Activating Token Index: 318

Text #10

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.6077. Min Act: 0.0001

Data Index: 950062 (C4 (Web Text))

Max Activating Token Index: 792

Text #11

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.5755. Min Act: 0.0000

Data Index: 140002 (C4 (Web Text))

Max Activating Token Index: 983

Text #12

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.5781. Min Act: 0.0000

Data Index: 884970 (C4 (Web Text))

Max Activating Token Index: 899

Text #13

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.5779. Min Act: 0.0001

Data Index: 933148 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.5455. Min Act: -0.0000

Data Index: 331339 (C4 (Web Text))

Max Activating Token Index: 814

Text #15

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.5667. Min Act: 0.0000

Data Index: 913772 (C4 (Web Text))

Max Activating Token Index: 691

Text #16

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.5818. Min Act: 0.0000

Data Index: 1141796 (C4 (Web Text))

Max Activating Token Index: 915

Text #17

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.5273. Min Act: 0.0000

Data Index: 318624 (C4 (Web Text))

Max Activating Token Index: 607

Text #18

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.5169. Min Act: -0.0000

Data Index: 128190 (C4 (Web Text))

Max Activating Token Index: 814

Text #19

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.4563. Min Act: -0.0000

Data Index: 711744 (C4 (Web Text))

Max Activating Token Index: 125