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

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

Neuron 5460 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8473. Min Range: -1.8473

Max Act: 1.8473. Min Act: -0.0000

Data Index: 433804 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 1.8473. Min Range: -1.8473

Max Act: 1.6908. Min Act: -0.0000

Data Index: 1477196 (Python Code)

Max Activating Token Index: 29

Text #2

Max Range: 1.8473. Min Range: -1.8473

Max Act: 1.7000. Min Act: -0.0000

Data Index: 1296963 (C4 (Web Text))

Max Activating Token Index: 438

Text #3

Max Range: 1.8473. Min Range: -1.8473

Max Act: 1.6945. Min Act: -0.0000

Data Index: 1523330 (Python Code)

Max Activating Token Index: 795

Text #4

Max Range: 1.8473. Min Range: -1.8473

Max Act: 1.5770. Min Act: -0.0000

Data Index: 406132 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 1.8473. Min Range: -1.8473

Max Act: 1.6353. Min Act: -0.0000

Data Index: 1588303 (Python Code)

Max Activating Token Index: 144

Text #6

Max Range: 1.8473. Min Range: -1.8473

Max Act: 1.5373. Min Act: -0.0000

Data Index: 1588098 (Python Code)

Max Activating Token Index: 481

Text #7

Max Range: 1.8473. Min Range: -1.8473

Max Act: 1.5859. Min Act: -0.0000

Data Index: 1060479 (C4 (Web Text))

Max Activating Token Index: 75

Text #8

Max Range: 1.8473. Min Range: -1.8473

Max Act: 1.4989. Min Act: -0.0000

Data Index: 1578066 (Python Code)

Max Activating Token Index: 121

Text #9

Max Range: 1.8473. Min Range: -1.8473

Max Act: 1.5717. Min Act: -0.0000

Data Index: 1528823 (Python Code)

Max Activating Token Index: 258

Text #10

Max Range: 1.8473. Min Range: -1.8473

Max Act: 1.4894. Min Act: -0.0000

Data Index: 798069 (C4 (Web Text))

Max Activating Token Index: 512

Text #11

Max Range: 1.8473. Min Range: -1.8473

Max Act: 1.5716. Min Act: -0.0000

Data Index: 1392530 (Python Code)

Max Activating Token Index: 563

Text #12

Max Range: 1.8473. Min Range: -1.8473

Max Act: 1.5708. Min Act: -0.0000

Data Index: 974898 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 1.8473. Min Range: -1.8473

Max Act: 1.4557. Min Act: -0.0000

Data Index: 1417923 (Python Code)

Max Activating Token Index: 236

Text #14

Max Range: 1.8473. Min Range: -1.8473

Max Act: 1.5682. Min Act: -0.0000

Data Index: 1587884 (Python Code)

Max Activating Token Index: 917

Text #15

Max Range: 1.8473. Min Range: -1.8473

Max Act: 1.5318. Min Act: -0.0000

Data Index: 1612250 (Python Code)

Max Activating Token Index: 978

Text #16

Max Range: 1.8473. Min Range: -1.8473

Max Act: 1.5273. Min Act: -0.0000

Data Index: 1442735 (Python Code)

Max Activating Token Index: 274

Text #17

Max Range: 1.8473. Min Range: -1.8473

Max Act: 1.5236. Min Act: -0.0000

Data Index: 1541335 (Python Code)

Max Activating Token Index: 725

Text #18

Max Range: 1.8473. Min Range: -1.8473

Max Act: 1.5216. Min Act: -0.0000

Data Index: 1640183 (Python Code)

Max Activating Token Index: 91

Text #19

Max Range: 1.8473. Min Range: -1.8473

Max Act: 1.5064. Min Act: -0.0000

Data Index: 1462481 (Python Code)

Max Activating Token Index: 466