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

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

Neuron 2857 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: 0.5897. Min Range: -0.5897

Max Act: 0.5897. Min Act: -0.0000

Data Index: 940923 (C4 (Web Text))

Max Activating Token Index: 435

Text #1

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.5155. Min Act: -0.0000

Data Index: 823717 (C4 (Web Text))

Max Activating Token Index: 303

Text #2

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.4596. Min Act: -0.0000

Data Index: 71725 (C4 (Web Text))

Max Activating Token Index: 803

Text #3

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.4624. Min Act: -0.0000

Data Index: 177393 (C4 (Web Text))

Max Activating Token Index: 900

Text #4

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.4785. Min Act: -0.0000

Data Index: 372267 (C4 (Web Text))

Max Activating Token Index: 891

Text #5

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.4211. Min Act: -0.0000

Data Index: 1057905 (C4 (Web Text))

Max Activating Token Index: 996

Text #6

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.4069. Min Act: -0.0000

Data Index: 987761 (C4 (Web Text))

Max Activating Token Index: 234

Text #7

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.3930. Min Act: -0.0000

Data Index: 273539 (C4 (Web Text))

Max Activating Token Index: 922

Text #8

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.4060. Min Act: -0.0000

Data Index: 434100 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.4081. Min Act: -0.0000

Data Index: 574240 (C4 (Web Text))

Max Activating Token Index: 853

Text #10

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.3917. Min Act: -0.0000

Data Index: 1326000 (C4 (Web Text))

Max Activating Token Index: 314

Text #11

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.3753. Min Act: -0.0000

Data Index: 828605 (C4 (Web Text))

Max Activating Token Index: 729

Text #12

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.3859. Min Act: -0.0000

Data Index: 1318319 (C4 (Web Text))

Max Activating Token Index: 868

Text #13

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.3923. Min Act: -0.0000

Data Index: 448801 (C4 (Web Text))

Max Activating Token Index: 89

Text #14

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.3912. Min Act: -0.0000

Data Index: 1045556 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.3599. Min Act: -0.0000

Data Index: 828827 (C4 (Web Text))

Max Activating Token Index: 475

Text #16

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.3775. Min Act: -0.0000

Data Index: 919959 (C4 (Web Text))

Max Activating Token Index: 743

Text #17

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.3445. Min Act: -0.0000

Data Index: 1057043 (C4 (Web Text))

Max Activating Token Index: 882

Text #18

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.3452. Min Act: -0.0000

Data Index: 1355728 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.3844. Min Act: -0.0000

Data Index: 895238 (C4 (Web Text))

Max Activating Token Index: 304