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

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

Neuron 3381 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2774. Min Range: -1.2774

Max Act: 1.1323. Min Act: -0.0000

Data Index: 1465716 (Python Code)

Max Activating Token Index: 869

Text #1

Max Range: 1.2774. Min Range: -1.2774

Max Act: 1.2774. Min Act: -0.0000

Data Index: 1615454 (Python Code)

Max Activating Token Index: 1008

Text #2

Max Range: 1.2774. Min Range: -1.2774

Max Act: 1.0426. Min Act: -0.0000

Data Index: 428009 (C4 (Web Text))

Max Activating Token Index: 458

Text #3

Max Range: 1.2774. Min Range: -1.2774

Max Act: 1.0765. Min Act: -0.0000

Data Index: 1620052 (Python Code)

Max Activating Token Index: 288

Text #4

Max Range: 1.2774. Min Range: -1.2774

Max Act: 1.0124. Min Act: -0.0000

Data Index: 16690 (C4 (Web Text))

Max Activating Token Index: 429

Text #5

Max Range: 1.2774. Min Range: -1.2774

Max Act: 1.0183. Min Act: -0.0000

Data Index: 1560911 (Python Code)

Max Activating Token Index: 818

Text #6

Max Range: 1.2774. Min Range: -1.2774

Max Act: 0.9918. Min Act: -0.0000

Data Index: 1338767 (C4 (Web Text))

Max Activating Token Index: 356

Text #7

Max Range: 1.2774. Min Range: -1.2774

Max Act: 0.9037. Min Act: -0.0000

Data Index: 458503 (C4 (Web Text))

Max Activating Token Index: 914

Text #8

Max Range: 1.2774. Min Range: -1.2774

Max Act: 0.9649. Min Act: -0.0000

Data Index: 1432877 (Python Code)

Max Activating Token Index: 686

Text #9

Max Range: 1.2774. Min Range: -1.2774

Max Act: 0.9711. Min Act: -0.0000

Data Index: 1370744 (Python Code)

Max Activating Token Index: 162

Text #10

Max Range: 1.2774. Min Range: -1.2774

Max Act: 0.8970. Min Act: -0.0000

Data Index: 1450767 (Python Code)

Max Activating Token Index: 724

Text #11

Max Range: 1.2774. Min Range: -1.2774

Max Act: 0.8321. Min Act: -0.0000

Data Index: 1555450 (Python Code)

Max Activating Token Index: 959

Text #12

Max Range: 1.2774. Min Range: -1.2774

Max Act: 0.8535. Min Act: -0.0000

Data Index: 1428378 (Python Code)

Max Activating Token Index: 309

Text #13

Max Range: 1.2774. Min Range: -1.2774

Max Act: 0.9468. Min Act: -0.0000

Data Index: 1066960 (C4 (Web Text))

Max Activating Token Index: 870

Text #14

Max Range: 1.2774. Min Range: -1.2774

Max Act: 0.9167. Min Act: -0.0000

Data Index: 1065969 (C4 (Web Text))

Max Activating Token Index: 716

Text #15

Max Range: 1.2774. Min Range: -1.2774

Max Act: 0.8844. Min Act: -0.0000

Data Index: 112010 (C4 (Web Text))

Max Activating Token Index: 739

Text #16

Max Range: 1.2774. Min Range: -1.2774

Max Act: 0.9039. Min Act: -0.0000

Data Index: 1499757 (Python Code)

Max Activating Token Index: 140

Text #17

Max Range: 1.2774. Min Range: -1.2774

Max Act: 0.8501. Min Act: -0.0000

Data Index: 1642054 (Python Code)

Max Activating Token Index: 89

Text #18

Max Range: 1.2774. Min Range: -1.2774

Max Act: 0.8343. Min Act: -0.0000

Data Index: 1029101 (C4 (Web Text))

Max Activating Token Index: 923

Text #19

Max Range: 1.2774. Min Range: -1.2774

Max Act: 0.9200. Min Act: -0.0000

Data Index: 1276674 (C4 (Web Text))

Max Activating Token Index: 743