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

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

Neuron 839 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1757. Min Range: -1.1757

Max Act: 1.0726. Min Act: -0.0000

Data Index: 1487847 (Python Code)

Max Activating Token Index: 209

Text #1

Max Range: 1.1757. Min Range: -1.1757

Max Act: 1.1479. Min Act: -0.0000

Data Index: 482793 (C4 (Web Text))

Max Activating Token Index: 329

Text #2

Max Range: 1.1757. Min Range: -1.1757

Max Act: 1.1757. Min Act: -0.0000

Data Index: 127104 (C4 (Web Text))

Max Activating Token Index: 236

Text #3

Max Range: 1.1757. Min Range: -1.1757

Max Act: 1.0898. Min Act: -0.0000

Data Index: 1075839 (C4 (Web Text))

Max Activating Token Index: 427

Text #4

Max Range: 1.1757. Min Range: -1.1757

Max Act: 1.0458. Min Act: -0.0000

Data Index: 658580 (C4 (Web Text))

Max Activating Token Index: 719

Text #5

Max Range: 1.1757. Min Range: -1.1757

Max Act: 1.0076. Min Act: -0.0000

Data Index: 777709 (C4 (Web Text))

Max Activating Token Index: 346

Text #6

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.9521. Min Act: -0.0000

Data Index: 394613 (C4 (Web Text))

Max Activating Token Index: 883

Text #7

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.8882. Min Act: -0.0000

Data Index: 382857 (C4 (Web Text))

Max Activating Token Index: 595

Text #8

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.8777. Min Act: -0.0000

Data Index: 990538 (C4 (Web Text))

Max Activating Token Index: 511

Text #9

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.9488. Min Act: -0.0000

Data Index: 370490 (C4 (Web Text))

Max Activating Token Index: 993

Text #10

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.8890. Min Act: -0.0000

Data Index: 752246 (C4 (Web Text))

Max Activating Token Index: 1018

Text #11

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.8551. Min Act: -0.0000

Data Index: 1533664 (Python Code)

Max Activating Token Index: 250

Text #12

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.8567. Min Act: -0.0000

Data Index: 1524599 (Python Code)

Max Activating Token Index: 107

Text #13

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.8201. Min Act: -0.0000

Data Index: 788104 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.8394. Min Act: -0.0000

Data Index: 1654760 (Python Code)

Max Activating Token Index: 604

Text #15

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.7576. Min Act: -0.0000

Data Index: 1253544 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.7623. Min Act: -0.0000

Data Index: 143828 (C4 (Web Text))

Max Activating Token Index: 511

Text #17

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.6598. Min Act: 0.0002

Data Index: 259219 (C4 (Web Text))

Max Activating Token Index: 925

Text #18

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.7301. Min Act: 0.0002

Data Index: 512302 (C4 (Web Text))

Max Activating Token Index: 428

Text #19

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.7528. Min Act: -0.0000

Data Index: 699340 (C4 (Web Text))

Max Activating Token Index: 596