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

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

Neuron 4697 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8322. Min Range: -0.8322

Max Act: 0.7796. Min Act: -0.0000

Data Index: 1068262 (C4 (Web Text))

Max Activating Token Index: 981

Text #1

Max Range: 0.8322. Min Range: -0.8322

Max Act: 0.7417. Min Act: -0.0000

Data Index: 522551 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 0.8322. Min Range: -0.8322

Max Act: 0.7262. Min Act: -0.0000

Data Index: 935648 (C4 (Web Text))

Max Activating Token Index: 299

Text #3

Max Range: 0.8322. Min Range: -0.8322

Max Act: 0.8322. Min Act: -0.0000

Data Index: 79383 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 0.8322. Min Range: -0.8322

Max Act: 0.7072. Min Act: -0.0000

Data Index: 1333740 (C4 (Web Text))

Max Activating Token Index: 836

Text #5

Max Range: 0.8322. Min Range: -0.8322

Max Act: 0.7616. Min Act: -0.0000

Data Index: 110036 (C4 (Web Text))

Max Activating Token Index: 136

Text #6

Max Range: 0.8322. Min Range: -0.8322

Max Act: 0.7342. Min Act: -0.0000

Data Index: 811743 (C4 (Web Text))

Max Activating Token Index: 694

Text #7

Max Range: 0.8322. Min Range: -0.8322

Max Act: 0.6783. Min Act: -0.0000

Data Index: 1197338 (C4 (Web Text))

Max Activating Token Index: 747

Text #8

Max Range: 0.8322. Min Range: -0.8322

Max Act: 0.6988. Min Act: -0.0000

Data Index: 1148510 (C4 (Web Text))

Max Activating Token Index: 281

Text #9

Max Range: 0.8322. Min Range: -0.8322

Max Act: 0.7293. Min Act: -0.0000

Data Index: 6106 (C4 (Web Text))

Max Activating Token Index: 1014

Text #10

Max Range: 0.8322. Min Range: -0.8322

Max Act: 0.6364. Min Act: -0.0000

Data Index: 83857 (C4 (Web Text))

Max Activating Token Index: 873

Text #11

Max Range: 0.8322. Min Range: -0.8322

Max Act: 0.6164. Min Act: -0.0000

Data Index: 340722 (C4 (Web Text))

Max Activating Token Index: 951

Text #12

Max Range: 0.8322. Min Range: -0.8322

Max Act: 0.6332. Min Act: -0.0000

Data Index: 904472 (C4 (Web Text))

Max Activating Token Index: 704

Text #13

Max Range: 0.8322. Min Range: -0.8322

Max Act: 0.6165. Min Act: -0.0000

Data Index: 388117 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 0.8322. Min Range: -0.8322

Max Act: 0.5715. Min Act: -0.0000

Data Index: 683410 (C4 (Web Text))

Max Activating Token Index: 524

Text #15

Max Range: 0.8322. Min Range: -0.8322

Max Act: 0.6083. Min Act: -0.0000

Data Index: 202261 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 0.8322. Min Range: -0.8322

Max Act: 0.5699. Min Act: -0.0000

Data Index: 648179 (C4 (Web Text))

Max Activating Token Index: 755

Text #17

Max Range: 0.8322. Min Range: -0.8322

Max Act: 0.5567. Min Act: -0.0000

Data Index: 56919 (C4 (Web Text))

Max Activating Token Index: 339

Text #18

Max Range: 0.8322. Min Range: -0.8322

Max Act: 0.5599. Min Act: -0.0000

Data Index: 335935 (C4 (Web Text))

Max Activating Token Index: 577

Text #19

Max Range: 0.8322. Min Range: -0.8322

Max Act: 0.5410. Min Act: -0.0000

Data Index: 947252 (C4 (Web Text))

Max Activating Token Index: 884