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

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

Neuron 3307 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: 0.7499. Min Range: -0.7499

Max Act: 0.7499. Min Act: -0.0000

Data Index: 590939 (C4 (Web Text))

Max Activating Token Index: 585

Text #1

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.6601. Min Act: -0.0000

Data Index: 71905 (C4 (Web Text))

Max Activating Token Index: 766

Text #2

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.7139. Min Act: -0.0000

Data Index: 147696 (C4 (Web Text))

Max Activating Token Index: 704

Text #3

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.6710. Min Act: -0.0000

Data Index: 1217923 (C4 (Web Text))

Max Activating Token Index: 59

Text #4

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.6460. Min Act: -0.0000

Data Index: 851008 (C4 (Web Text))

Max Activating Token Index: 706

Text #5

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.6341. Min Act: -0.0000

Data Index: 162021 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.6355. Min Act: -0.0001

Data Index: 1243551 (C4 (Web Text))

Max Activating Token Index: 712

Text #7

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.6022. Min Act: -0.0000

Data Index: 430712 (C4 (Web Text))

Max Activating Token Index: 577

Text #8

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.6150. Min Act: -0.0000

Data Index: 886879 (C4 (Web Text))

Max Activating Token Index: 100

Text #9

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.5866. Min Act: -0.0000

Data Index: 943034 (C4 (Web Text))

Max Activating Token Index: 471

Text #10

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.6081. Min Act: -0.0001

Data Index: 1099706 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.5987. Min Act: -0.0000

Data Index: 1238585 (C4 (Web Text))

Max Activating Token Index: 220

Text #12

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.5942. Min Act: -0.0001

Data Index: 125464 (C4 (Web Text))

Max Activating Token Index: 1015

Text #13

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.4726. Min Act: -0.0000

Data Index: 620656 (C4 (Web Text))

Max Activating Token Index: 545

Text #14

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.5840. Min Act: -0.0000

Data Index: 612446 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.5837. Min Act: -0.0000

Data Index: 730376 (C4 (Web Text))

Max Activating Token Index: 675

Text #16

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.5519. Min Act: -0.0000

Data Index: 1197560 (C4 (Web Text))

Max Activating Token Index: 896

Text #17

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.6070. Min Act: -0.0000

Data Index: 1122825 (C4 (Web Text))

Max Activating Token Index: 367

Text #18

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.5835. Min Act: -0.0000

Data Index: 748359 (C4 (Web Text))

Max Activating Token Index: 449

Text #19

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.5457. Min Act: -0.0000

Data Index: 633139 (C4 (Web Text))

Max Activating Token Index: 344