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

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

Neuron 442 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: 0.1268. Min Range: -0.1268

Max Act: 0.1268. Min Act: -0.0000

Data Index: 1600112 (Python Code)

Max Activating Token Index: 129

Text #1

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.1115. Min Act: -0.0000

Data Index: 540276 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.1033. Min Act: -0.0000

Data Index: 740288 (C4 (Web Text))

Max Activating Token Index: 998

Text #3

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.1009. Min Act: -0.0000

Data Index: 1531716 (Python Code)

Max Activating Token Index: 483

Text #4

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.1111. Min Act: -0.0000

Data Index: 316701 (C4 (Web Text))

Max Activating Token Index: 405

Text #5

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.1032. Min Act: -0.0000

Data Index: 954514 (C4 (Web Text))

Max Activating Token Index: 949

Text #6

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.0953. Min Act: -0.0000

Data Index: 710207 (C4 (Web Text))

Max Activating Token Index: 332

Text #7

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.0892. Min Act: -0.0000

Data Index: 746764 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.0869. Min Act: -0.0000

Data Index: 1046046 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.1042. Min Act: -0.0000

Data Index: 1519461 (Python Code)

Max Activating Token Index: 355

Text #10

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.0908. Min Act: -0.0000

Data Index: 1258201 (C4 (Web Text))

Max Activating Token Index: 725

Text #11

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.0949. Min Act: -0.0000

Data Index: 1293820 (C4 (Web Text))

Max Activating Token Index: 689

Text #12

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.0874. Min Act: -0.0000

Data Index: 1350479 (C4 (Web Text))

Max Activating Token Index: 125

Text #13

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.0867. Min Act: -0.0000

Data Index: 470343 (C4 (Web Text))

Max Activating Token Index: 640

Text #14

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.0832. Min Act: -0.0000

Data Index: 567625 (C4 (Web Text))

Max Activating Token Index: 510

Text #15

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.0820. Min Act: -0.0000

Data Index: 1564672 (Python Code)

Max Activating Token Index: 30

Text #16

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.0898. Min Act: -0.0000

Data Index: 159200 (C4 (Web Text))

Max Activating Token Index: 893

Text #17

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.0858. Min Act: -0.0000

Data Index: 70976 (C4 (Web Text))

Max Activating Token Index: 362

Text #18

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.0833. Min Act: -0.0000

Data Index: 1365742 (Python Code)

Max Activating Token Index: 939

Text #19

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.0786. Min Act: -0.0000

Data Index: 816245 (C4 (Web Text))

Max Activating Token Index: 220