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

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

Neuron 1096 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: 1.3371. Min Range: -1.3371

Max Act: 1.2649. Min Act: -0.0000

Data Index: 1494850 (Python Code)

Max Activating Token Index: 678

Text #1

Max Range: 1.3371. Min Range: -1.3371

Max Act: 1.2405. Min Act: -0.0000

Data Index: 1509079 (Python Code)

Max Activating Token Index: 892

Text #2

Max Range: 1.3371. Min Range: -1.3371

Max Act: 1.2668. Min Act: -0.0000

Data Index: 1502243 (Python Code)

Max Activating Token Index: 849

Text #3

Max Range: 1.3371. Min Range: -1.3371

Max Act: 1.3371. Min Act: -0.0000

Data Index: 965244 (C4 (Web Text))

Max Activating Token Index: 80

Text #4

Max Range: 1.3371. Min Range: -1.3371

Max Act: 1.1913. Min Act: -0.0000

Data Index: 1541907 (Python Code)

Max Activating Token Index: 972

Text #5

Max Range: 1.3371. Min Range: -1.3371

Max Act: 1.1384. Min Act: -0.0000

Data Index: 1428866 (Python Code)

Max Activating Token Index: 631

Text #6

Max Range: 1.3371. Min Range: -1.3371

Max Act: 1.2051. Min Act: -0.0000

Data Index: 1599751 (Python Code)

Max Activating Token Index: 616

Text #7

Max Range: 1.3371. Min Range: -1.3371

Max Act: 1.1219. Min Act: -0.0000

Data Index: 1605436 (Python Code)

Max Activating Token Index: 681

Text #8

Max Range: 1.3371. Min Range: -1.3371

Max Act: 1.1450. Min Act: -0.0000

Data Index: 1488228 (Python Code)

Max Activating Token Index: 843

Text #9

Max Range: 1.3371. Min Range: -1.3371

Max Act: 1.1510. Min Act: -0.0000

Data Index: 1597231 (Python Code)

Max Activating Token Index: 709

Text #10

Max Range: 1.3371. Min Range: -1.3371

Max Act: 1.2038. Min Act: -0.0000

Data Index: 1611210 (Python Code)

Max Activating Token Index: 369

Text #11

Max Range: 1.3371. Min Range: -1.3371

Max Act: 1.1351. Min Act: -0.0000

Data Index: 1506768 (Python Code)

Max Activating Token Index: 327

Text #12

Max Range: 1.3371. Min Range: -1.3371

Max Act: 1.0974. Min Act: -0.0000

Data Index: 1561967 (Python Code)

Max Activating Token Index: 346

Text #13

Max Range: 1.3371. Min Range: -1.3371

Max Act: 1.0967. Min Act: -0.0000

Data Index: 1634303 (Python Code)

Max Activating Token Index: 26

Text #14

Max Range: 1.3371. Min Range: -1.3371

Max Act: 1.1173. Min Act: -0.0000

Data Index: 1142324 (C4 (Web Text))

Max Activating Token Index: 610

Text #15

Max Range: 1.3371. Min Range: -1.3371

Max Act: 1.1801. Min Act: -0.0000

Data Index: 1516728 (Python Code)

Max Activating Token Index: 117

Text #16

Max Range: 1.3371. Min Range: -1.3371

Max Act: 1.1459. Min Act: -0.0000

Data Index: 1644024 (Python Code)

Max Activating Token Index: 19

Text #17

Max Range: 1.3371. Min Range: -1.3371

Max Act: 1.1127. Min Act: -0.0000

Data Index: 1365985 (Python Code)

Max Activating Token Index: 468

Text #18

Max Range: 1.3371. Min Range: -1.3371

Max Act: 1.1308. Min Act: -0.0000

Data Index: 1552680 (Python Code)

Max Activating Token Index: 298

Text #19

Max Range: 1.3371. Min Range: -1.3371

Max Act: 1.1576. Min Act: -0.0000

Data Index: 1446999 (Python Code)

Max Activating Token Index: 714