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

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

Neuron 687 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: 3.8415. Min Range: -3.8415

Max Act: 3.7708. Min Act: -0.0000

Data Index: 1530944 (Python Code)

Max Activating Token Index: 495

Text #1

Max Range: 3.8415. Min Range: -3.8415

Max Act: 3.8415. Min Act: -0.0000

Data Index: 1587398 (Python Code)

Max Activating Token Index: 314

Text #2

Max Range: 3.8415. Min Range: -3.8415

Max Act: 3.7630. Min Act: -0.0000

Data Index: 1482684 (Python Code)

Max Activating Token Index: 485

Text #3

Max Range: 3.8415. Min Range: -3.8415

Max Act: 3.7112. Min Act: -0.0000

Data Index: 1365224 (Python Code)

Max Activating Token Index: 738

Text #4

Max Range: 3.8415. Min Range: -3.8415

Max Act: 3.6252. Min Act: -0.0000

Data Index: 1608620 (Python Code)

Max Activating Token Index: 779

Text #5

Max Range: 3.8415. Min Range: -3.8415

Max Act: 3.7116. Min Act: -0.0000

Data Index: 1448238 (Python Code)

Max Activating Token Index: 74

Text #6

Max Range: 3.8415. Min Range: -3.8415

Max Act: 3.4859. Min Act: -0.0000

Data Index: 1493275 (Python Code)

Max Activating Token Index: 663

Text #7

Max Range: 3.8415. Min Range: -3.8415

Max Act: 3.1188. Min Act: -0.0000

Data Index: 1363963 (Python Code)

Max Activating Token Index: 667

Text #8

Max Range: 3.8415. Min Range: -3.8415

Max Act: 3.3861. Min Act: -0.0000

Data Index: 1596346 (Python Code)

Max Activating Token Index: 566

Text #9

Max Range: 3.8415. Min Range: -3.8415

Max Act: 3.1963. Min Act: -0.0000

Data Index: 1418745 (Python Code)

Max Activating Token Index: 114

Text #10

Max Range: 3.8415. Min Range: -3.8415

Max Act: 3.4596. Min Act: -0.0000

Data Index: 1644590 (Python Code)

Max Activating Token Index: 92

Text #11

Max Range: 3.8415. Min Range: -3.8415

Max Act: 3.2875. Min Act: -0.0000

Data Index: 1633795 (Python Code)

Max Activating Token Index: 492

Text #12

Max Range: 3.8415. Min Range: -3.8415

Max Act: 3.2765. Min Act: -0.0000

Data Index: 1441583 (Python Code)

Max Activating Token Index: 149

Text #13

Max Range: 3.8415. Min Range: -3.8415

Max Act: 3.2462. Min Act: -0.0000

Data Index: 1441446 (Python Code)

Max Activating Token Index: 921

Text #14

Max Range: 3.8415. Min Range: -3.8415

Max Act: 3.0652. Min Act: -0.0000

Data Index: 1596838 (Python Code)

Max Activating Token Index: 493

Text #15

Max Range: 3.8415. Min Range: -3.8415

Max Act: 3.3980. Min Act: -0.0000

Data Index: 1463182 (Python Code)

Max Activating Token Index: 671

Text #16

Max Range: 3.8415. Min Range: -3.8415

Max Act: 2.8872. Min Act: -0.0000

Data Index: 1481929 (Python Code)

Max Activating Token Index: 785

Text #17

Max Range: 3.8415. Min Range: -3.8415

Max Act: 3.2733. Min Act: -0.0000

Data Index: 1477348 (Python Code)

Max Activating Token Index: 900

Text #18

Max Range: 3.8415. Min Range: -3.8415

Max Act: 2.9739. Min Act: -0.0000

Data Index: 1564209 (Python Code)

Max Activating Token Index: 555

Text #19

Max Range: 3.8415. Min Range: -3.8415

Max Act: 3.1315. Min Act: -0.0000

Data Index: 1489779 (Python Code)

Max Activating Token Index: 203