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

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

Neuron 2666 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1978. Min Act: -0.0000

Data Index: 157658 (C4 (Web Text))

Max Activating Token Index: 303

Text #1

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.0993. Min Act: -0.0000

Data Index: 1166009 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1013. Min Act: -0.0000

Data Index: 1094480 (C4 (Web Text))

Max Activating Token Index: 243

Text #3

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.0889. Min Act: -0.0000

Data Index: 1561994 (Python Code)

Max Activating Token Index: 729

Text #4

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.0991. Min Act: -0.0000

Data Index: 181972 (C4 (Web Text))

Max Activating Token Index: 989

Text #5

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.0909. Min Act: -0.0000

Data Index: 1645045 (Python Code)

Max Activating Token Index: 40

Text #6

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.0902. Min Act: -0.0000

Data Index: 1483326 (Python Code)

Max Activating Token Index: 185

Text #7

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.0874. Min Act: -0.0000

Data Index: 334582 (C4 (Web Text))

Max Activating Token Index: 138

Text #8

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.0894. Min Act: -0.0000

Data Index: 706555 (C4 (Web Text))

Max Activating Token Index: 471

Text #9

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.0912. Min Act: -0.0000

Data Index: 1505226 (Python Code)

Max Activating Token Index: 540

Text #10

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.0910. Min Act: -0.0000

Data Index: 1425442 (Python Code)

Max Activating Token Index: 340

Text #11

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.0893. Min Act: -0.0000

Data Index: 939023 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.0910. Min Act: -0.0000

Data Index: 1402955 (Python Code)

Max Activating Token Index: 634

Text #13

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.0860. Min Act: -0.0000

Data Index: 170392 (C4 (Web Text))

Max Activating Token Index: 621

Text #14

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.0885. Min Act: -0.0000

Data Index: 1306880 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.0849. Min Act: -0.0000

Data Index: 375567 (C4 (Web Text))

Max Activating Token Index: 590

Text #16

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.0914. Min Act: -0.0000

Data Index: 571393 (C4 (Web Text))

Max Activating Token Index: 264

Text #17

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.0873. Min Act: -0.0000

Data Index: 751567 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.0878. Min Act: -0.0000

Data Index: 65995 (C4 (Web Text))

Max Activating Token Index: 732

Text #19

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.0897. Min Act: -0.0000

Data Index: 474881 (C4 (Web Text))

Max Activating Token Index: 199