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

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

Neuron 1307 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: 0.8864. Min Range: -0.8864

Max Act: 0.8864. Min Act: -0.0000

Data Index: 1649071 (Python Code)

Max Activating Token Index: 705

Text #1

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.7876. Min Act: -0.0000

Data Index: 1361469 (Python Code)

Max Activating Token Index: 868

Text #2

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.8262. Min Act: -0.0000

Data Index: 1446418 (Python Code)

Max Activating Token Index: 235

Text #3

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.7880. Min Act: -0.0000

Data Index: 1370817 (Python Code)

Max Activating Token Index: 49

Text #4

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.8112. Min Act: -0.0000

Data Index: 1459740 (Python Code)

Max Activating Token Index: 167

Text #5

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.7839. Min Act: -0.0000

Data Index: 1450734 (Python Code)

Max Activating Token Index: 212

Text #6

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.7725. Min Act: -0.0000

Data Index: 1509204 (Python Code)

Max Activating Token Index: 581

Text #7

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.8012. Min Act: -0.0000

Data Index: 1367083 (Python Code)

Max Activating Token Index: 492

Text #8

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.7735. Min Act: -0.0000

Data Index: 1516254 (Python Code)

Max Activating Token Index: 63

Text #9

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.7684. Min Act: -0.0000

Data Index: 1471225 (Python Code)

Max Activating Token Index: 964

Text #10

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.7626. Min Act: -0.0000

Data Index: 1454881 (Python Code)

Max Activating Token Index: 1007

Text #11

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.7169. Min Act: -0.0000

Data Index: 1375491 (Python Code)

Max Activating Token Index: 352

Text #12

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.7620. Min Act: -0.0000

Data Index: 1499196 (Python Code)

Max Activating Token Index: 114

Text #13

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.7246. Min Act: -0.0000

Data Index: 1593724 (Python Code)

Max Activating Token Index: 329

Text #14

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.7867. Min Act: -0.0000

Data Index: 1560330 (Python Code)

Max Activating Token Index: 966

Text #15

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.7397. Min Act: -0.0000

Data Index: 1567335 (Python Code)

Max Activating Token Index: 316

Text #16

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.7307. Min Act: -0.0000

Data Index: 1465741 (Python Code)

Max Activating Token Index: 60

Text #17

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.7331. Min Act: -0.0000

Data Index: 1398168 (Python Code)

Max Activating Token Index: 498

Text #18

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.7075. Min Act: -0.0000

Data Index: 1402376 (Python Code)

Max Activating Token Index: 740

Text #19

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.7278. Min Act: -0.0000

Data Index: 1392733 (Python Code)

Max Activating Token Index: 117