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

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

Neuron 2877 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5098. Min Range: -3.5098

Max Act: 3.3910. Min Act: -0.0000

Data Index: 1648970 (Python Code)

Max Activating Token Index: 934

Text #1

Max Range: 3.5098. Min Range: -3.5098

Max Act: 3.3301. Min Act: -0.0000

Data Index: 917862 (C4 (Web Text))

Max Activating Token Index: 486

Text #2

Max Range: 3.5098. Min Range: -3.5098

Max Act: 3.3313. Min Act: -0.0000

Data Index: 1271255 (C4 (Web Text))

Max Activating Token Index: 313

Text #3

Max Range: 3.5098. Min Range: -3.5098

Max Act: 3.5098. Min Act: -0.0000

Data Index: 1400074 (Python Code)

Max Activating Token Index: 321

Text #4

Max Range: 3.5098. Min Range: -3.5098

Max Act: 3.1409. Min Act: -0.0000

Data Index: 1362266 (Python Code)

Max Activating Token Index: 928

Text #5

Max Range: 3.5098. Min Range: -3.5098

Max Act: 3.1930. Min Act: -0.0000

Data Index: 1226767 (C4 (Web Text))

Max Activating Token Index: 448

Text #6

Max Range: 3.5098. Min Range: -3.5098

Max Act: 3.1303. Min Act: -0.0000

Data Index: 1390054 (Python Code)

Max Activating Token Index: 818

Text #7

Max Range: 3.5098. Min Range: -3.5098

Max Act: 3.3146. Min Act: -0.0000

Data Index: 935438 (C4 (Web Text))

Max Activating Token Index: 368

Text #8

Max Range: 3.5098. Min Range: -3.5098

Max Act: 2.7160. Min Act: -0.0000

Data Index: 1018326 (C4 (Web Text))

Max Activating Token Index: 797

Text #9

Max Range: 3.5098. Min Range: -3.5098

Max Act: 2.9784. Min Act: -0.0000

Data Index: 142292 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 3.5098. Min Range: -3.5098

Max Act: 3.2516. Min Act: -0.0000

Data Index: 1474747 (Python Code)

Max Activating Token Index: 123

Text #11

Max Range: 3.5098. Min Range: -3.5098

Max Act: 2.7952. Min Act: -0.0000

Data Index: 1532741 (Python Code)

Max Activating Token Index: 274

Text #12

Max Range: 3.5098. Min Range: -3.5098

Max Act: 3.0902. Min Act: -0.0000

Data Index: 1493151 (Python Code)

Max Activating Token Index: 392

Text #13

Max Range: 3.5098. Min Range: -3.5098

Max Act: 3.0194. Min Act: -0.0000

Data Index: 793571 (C4 (Web Text))

Max Activating Token Index: 588

Text #14

Max Range: 3.5098. Min Range: -3.5098

Max Act: 3.1581. Min Act: -0.0000

Data Index: 1126016 (C4 (Web Text))

Max Activating Token Index: 187

Text #15

Max Range: 3.5098. Min Range: -3.5098

Max Act: 3.1435. Min Act: -0.0000

Data Index: 398430 (C4 (Web Text))

Max Activating Token Index: 107

Text #16

Max Range: 3.5098. Min Range: -3.5098

Max Act: 2.7096. Min Act: -0.0000

Data Index: 544449 (C4 (Web Text))

Max Activating Token Index: 682

Text #17

Max Range: 3.5098. Min Range: -3.5098

Max Act: 3.1083. Min Act: -0.0000

Data Index: 835696 (C4 (Web Text))

Max Activating Token Index: 155

Text #18

Max Range: 3.5098. Min Range: -3.5098

Max Act: 2.4932. Min Act: -0.0000

Data Index: 1481662 (Python Code)

Max Activating Token Index: 405

Text #19

Max Range: 3.5098. Min Range: -3.5098

Max Act: 2.7835. Min Act: -0.0000

Data Index: 739101 (C4 (Web Text))

Max Activating Token Index: 911