Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1732 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2846. Min Act: -0.0000

Data Index: 1585681 (Python Code)

Max Activating Token Index: 144

Text #1

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.3088. Min Act: -0.0000

Data Index: 1537458 (Python Code)

Max Activating Token Index: 120

Text #2

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.3195. Min Act: -0.0000

Data Index: 1450112 (Python Code)

Max Activating Token Index: 330

Text #3

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.3099. Min Act: -0.0000

Data Index: 1428687 (Python Code)

Max Activating Token Index: 462

Text #4

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2716. Min Act: -0.0000

Data Index: 1423243 (Python Code)

Max Activating Token Index: 144

Text #5

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2719. Min Act: -0.0000

Data Index: 1459389 (Python Code)

Max Activating Token Index: 860

Text #6

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2628. Min Act: -0.0000

Data Index: 1480145 (Python Code)

Max Activating Token Index: 874

Text #7

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2870. Min Act: -0.0000

Data Index: 1364952 (Python Code)

Max Activating Token Index: 216

Text #8

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2552. Min Act: -0.0000

Data Index: 1577202 (Python Code)

Max Activating Token Index: 816

Text #9

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2638. Min Act: -0.0000

Data Index: 1508194 (Python Code)

Max Activating Token Index: 47

Text #10

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2412. Min Act: -0.0000

Data Index: 1655800 (Python Code)

Max Activating Token Index: 664

Text #11

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2674. Min Act: -0.0000

Data Index: 1418750 (Python Code)

Max Activating Token Index: 145

Text #12

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2506. Min Act: -0.0000

Data Index: 1440579 (Python Code)

Max Activating Token Index: 494

Text #13

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2338. Min Act: -0.0000

Data Index: 1594073 (Python Code)

Max Activating Token Index: 677

Text #14

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2180. Min Act: -0.0000

Data Index: 1399533 (Python Code)

Max Activating Token Index: 158

Text #15

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2582. Min Act: -0.0000

Data Index: 1650971 (Python Code)

Max Activating Token Index: 158

Text #16

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2171. Min Act: 0.0000

Data Index: 1468070 (Python Code)

Max Activating Token Index: 522

Text #17

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2464. Min Act: -0.0000

Data Index: 1631512 (Python Code)

Max Activating Token Index: 799

Text #18

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2313. Min Act: -0.0000

Data Index: 1395604 (Python Code)

Max Activating Token Index: 778

Text #19

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2085. Min Act: -0.0000

Data Index: 1488449 (Python Code)

Max Activating Token Index: 288