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

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

Neuron 559 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: 0.8065. Min Range: -0.8065

Max Act: 0.8065. Min Act: -0.0000

Data Index: 425155 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.8017. Min Act: -0.0000

Data Index: 852031 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.7868. Min Act: -0.0000

Data Index: 57747 (C4 (Web Text))

Max Activating Token Index: 288

Text #3

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.7797. Min Act: -0.0000

Data Index: 1099157 (C4 (Web Text))

Max Activating Token Index: 706

Text #4

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.7524. Min Act: -0.0000

Data Index: 877998 (C4 (Web Text))

Max Activating Token Index: 232

Text #5

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.7346. Min Act: -0.0000

Data Index: 287087 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.7287. Min Act: -0.0000

Data Index: 176503 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.6958. Min Act: -0.0000

Data Index: 124185 (C4 (Web Text))

Max Activating Token Index: 39

Text #8

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.7280. Min Act: -0.0000

Data Index: 49607 (C4 (Web Text))

Max Activating Token Index: 836

Text #9

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.6788. Min Act: -0.0000

Data Index: 867305 (C4 (Web Text))

Max Activating Token Index: 281

Text #10

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.6473. Min Act: -0.0000

Data Index: 1302678 (C4 (Web Text))

Max Activating Token Index: 669

Text #11

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.6760. Min Act: -0.0000

Data Index: 70124 (C4 (Web Text))

Max Activating Token Index: 5

Text #12

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.6929. Min Act: -0.0000

Data Index: 1017351 (C4 (Web Text))

Max Activating Token Index: 996

Text #13

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.6804. Min Act: -0.0000

Data Index: 845523 (C4 (Web Text))

Max Activating Token Index: 460

Text #14

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.6582. Min Act: -0.0000

Data Index: 590751 (C4 (Web Text))

Max Activating Token Index: 557

Text #15

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.6432. Min Act: -0.0000

Data Index: 1252011 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.6460. Min Act: -0.0000

Data Index: 498709 (C4 (Web Text))

Max Activating Token Index: 578

Text #17

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.5990. Min Act: -0.0000

Data Index: 852873 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.6288. Min Act: -0.0000

Data Index: 400506 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.6307. Min Act: -0.0000

Data Index: 745496 (C4 (Web Text))

Max Activating Token Index: 5