Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1796 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0476. Min Act: -0.0003

Data Index: 135303 (C4 (Web Text))

Max Activating Token Index: 922

Text #1

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0459. Min Act: -0.0003

Data Index: 417952 (C4 (Web Text))

Max Activating Token Index: 162

Text #2

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0458. Min Act: -0.0003

Data Index: 249725 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0468. Min Act: -0.0003

Data Index: 1276011 (C4 (Web Text))

Max Activating Token Index: 881

Text #4

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0457. Min Act: -0.0003

Data Index: 369654 (C4 (Web Text))

Max Activating Token Index: 6

Text #5

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0457. Min Act: -0.0003

Data Index: 1209279 (C4 (Web Text))

Max Activating Token Index: 766

Text #6

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0458. Min Act: -0.0003

Data Index: 1391923 (Python Code)

Max Activating Token Index: 262

Text #7

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0448. Min Act: -0.0003

Data Index: 143707 (C4 (Web Text))

Max Activating Token Index: 406

Text #8

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0430. Min Act: -0.0003

Data Index: 641983 (C4 (Web Text))

Max Activating Token Index: 127

Text #9

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0419. Min Act: -0.0003

Data Index: 103825 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0448. Min Act: -0.0003

Data Index: 1435395 (Python Code)

Max Activating Token Index: 981

Text #11

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0447. Min Act: -0.0003

Data Index: 407307 (C4 (Web Text))

Max Activating Token Index: 832

Text #12

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0434. Min Act: -0.0003

Data Index: 1231103 (C4 (Web Text))

Max Activating Token Index: 932

Text #13

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0421. Min Act: -0.0003

Data Index: 1086615 (C4 (Web Text))

Max Activating Token Index: 978

Text #14

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0429. Min Act: -0.0003

Data Index: 619233 (C4 (Web Text))

Max Activating Token Index: 320

Text #15

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0428. Min Act: -0.0003

Data Index: 1171924 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0429. Min Act: -0.0003

Data Index: 26479 (C4 (Web Text))

Max Activating Token Index: 174

Text #17

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0434. Min Act: -0.0003

Data Index: 725640 (C4 (Web Text))

Max Activating Token Index: 435

Text #18

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0436. Min Act: -0.0003

Data Index: 902793 (C4 (Web Text))

Max Activating Token Index: 135

Text #19

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0401. Min Act: -0.0003

Data Index: 850807 (C4 (Web Text))

Max Activating Token Index: 312