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

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

Neuron 5786 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7228. Min Range: -1.7228

Max Act: 1.7228. Min Act: -0.0000

Data Index: 1502337 (Python Code)

Max Activating Token Index: 41

Text #1

Max Range: 1.7228. Min Range: -1.7228

Max Act: 1.6355. Min Act: -0.0000

Data Index: 292911 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 1.7228. Min Range: -1.7228

Max Act: 1.6793. Min Act: -0.0000

Data Index: 544108 (C4 (Web Text))

Max Activating Token Index: 778

Text #3

Max Range: 1.7228. Min Range: -1.7228

Max Act: 1.5753. Min Act: -0.0000

Data Index: 871076 (C4 (Web Text))

Max Activating Token Index: 790

Text #4

Max Range: 1.7228. Min Range: -1.7228

Max Act: 1.5473. Min Act: -0.0000

Data Index: 803494 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 1.7228. Min Range: -1.7228

Max Act: 1.5456. Min Act: -0.0000

Data Index: 520277 (C4 (Web Text))

Max Activating Token Index: 443

Text #6

Max Range: 1.7228. Min Range: -1.7228

Max Act: 1.7192. Min Act: -0.0000

Data Index: 1623416 (Python Code)

Max Activating Token Index: 794

Text #7

Max Range: 1.7228. Min Range: -1.7228

Max Act: 1.6142. Min Act: -0.0000

Data Index: 1310904 (C4 (Web Text))

Max Activating Token Index: 261

Text #8

Max Range: 1.7228. Min Range: -1.7228

Max Act: 1.5163. Min Act: -0.0000

Data Index: 1492213 (Python Code)

Max Activating Token Index: 28

Text #9

Max Range: 1.7228. Min Range: -1.7228

Max Act: 1.5218. Min Act: -0.0000

Data Index: 1193792 (C4 (Web Text))

Max Activating Token Index: 816

Text #10

Max Range: 1.7228. Min Range: -1.7228

Max Act: 1.5815. Min Act: -0.0000

Data Index: 1522052 (Python Code)

Max Activating Token Index: 117

Text #11

Max Range: 1.7228. Min Range: -1.7228

Max Act: 1.6510. Min Act: -0.0000

Data Index: 250709 (C4 (Web Text))

Max Activating Token Index: 337

Text #12

Max Range: 1.7228. Min Range: -1.7228

Max Act: 1.5338. Min Act: -0.0000

Data Index: 189440 (C4 (Web Text))

Max Activating Token Index: 555

Text #13

Max Range: 1.7228. Min Range: -1.7228

Max Act: 1.4618. Min Act: -0.0000

Data Index: 1528942 (Python Code)

Max Activating Token Index: 539

Text #14

Max Range: 1.7228. Min Range: -1.7228

Max Act: 1.4112. Min Act: -0.0000

Data Index: 1380975 (Python Code)

Max Activating Token Index: 20

Text #15

Max Range: 1.7228. Min Range: -1.7228

Max Act: 1.4983. Min Act: -0.0000

Data Index: 356405 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 1.7228. Min Range: -1.7228

Max Act: 1.3375. Min Act: -0.0000

Data Index: 1545305 (Python Code)

Max Activating Token Index: 579

Text #17

Max Range: 1.7228. Min Range: -1.7228

Max Act: 1.4453. Min Act: -0.0000

Data Index: 297673 (C4 (Web Text))

Max Activating Token Index: 914

Text #18

Max Range: 1.7228. Min Range: -1.7228

Max Act: 1.3942. Min Act: -0.0000

Data Index: 1382965 (Python Code)

Max Activating Token Index: 1002

Text #19

Max Range: 1.7228. Min Range: -1.7228

Max Act: 1.4351. Min Act: -0.0000

Data Index: 662753 (C4 (Web Text))

Max Activating Token Index: 297