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

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

Neuron 1641 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: 1.9062. Min Range: -1.9062

Max Act: 1.9062. Min Act: -0.0000

Data Index: 1371339 (Python Code)

Max Activating Token Index: 426

Text #1

Max Range: 1.9062. Min Range: -1.9062

Max Act: 1.4643. Min Act: -0.0000

Data Index: 1208883 (C4 (Web Text))

Max Activating Token Index: 515

Text #2

Max Range: 1.9062. Min Range: -1.9062

Max Act: 1.4518. Min Act: -0.0000

Data Index: 1512452 (Python Code)

Max Activating Token Index: 223

Text #3

Max Range: 1.9062. Min Range: -1.9062

Max Act: 1.3645. Min Act: 0.0000

Data Index: 1646241 (Python Code)

Max Activating Token Index: 40

Text #4

Max Range: 1.9062. Min Range: -1.9062

Max Act: 1.3506. Min Act: -0.0000

Data Index: 1282596 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 1.9062. Min Range: -1.9062

Max Act: 1.2698. Min Act: -0.0000

Data Index: 778390 (C4 (Web Text))

Max Activating Token Index: 8

Text #6

Max Range: 1.9062. Min Range: -1.9062

Max Act: 1.2698. Min Act: -0.0000

Data Index: 758241 (C4 (Web Text))

Max Activating Token Index: 8

Text #7

Max Range: 1.9062. Min Range: -1.9062

Max Act: 1.2438. Min Act: -0.0000

Data Index: 1074350 (C4 (Web Text))

Max Activating Token Index: 759

Text #8

Max Range: 1.9062. Min Range: -1.9062

Max Act: 1.3417. Min Act: -0.0000

Data Index: 1588428 (Python Code)

Max Activating Token Index: 292

Text #9

Max Range: 1.9062. Min Range: -1.9062

Max Act: 1.2264. Min Act: -0.0000

Data Index: 786633 (C4 (Web Text))

Max Activating Token Index: 222

Text #10

Max Range: 1.9062. Min Range: -1.9062

Max Act: 1.1414. Min Act: -0.0000

Data Index: 1164862 (C4 (Web Text))

Max Activating Token Index: 819

Text #11

Max Range: 1.9062. Min Range: -1.9062

Max Act: 1.2052. Min Act: -0.0000

Data Index: 605390 (C4 (Web Text))

Max Activating Token Index: 890

Text #12

Max Range: 1.9062. Min Range: -1.9062

Max Act: 1.2293. Min Act: -0.0000

Data Index: 46748 (C4 (Web Text))

Max Activating Token Index: 187

Text #13

Max Range: 1.9062. Min Range: -1.9062

Max Act: 1.2355. Min Act: -0.0000

Data Index: 972384 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 1.9062. Min Range: -1.9062

Max Act: 1.1923. Min Act: -0.0000

Data Index: 519344 (C4 (Web Text))

Max Activating Token Index: 722

Text #15

Max Range: 1.9062. Min Range: -1.9062

Max Act: 1.2677. Min Act: -0.0000

Data Index: 1179682 (C4 (Web Text))

Max Activating Token Index: 709

Text #16

Max Range: 1.9062. Min Range: -1.9062

Max Act: 1.1659. Min Act: -0.0000

Data Index: 832874 (C4 (Web Text))

Max Activating Token Index: 689

Text #17

Max Range: 1.9062. Min Range: -1.9062

Max Act: 1.1511. Min Act: 0.0000

Data Index: 1465451 (Python Code)

Max Activating Token Index: 769

Text #18

Max Range: 1.9062. Min Range: -1.9062

Max Act: 1.1494. Min Act: -0.0000

Data Index: 1189905 (C4 (Web Text))

Max Activating Token Index: 89

Text #19

Max Range: 1.9062. Min Range: -1.9062

Max Act: 1.0855. Min Act: -0.0000

Data Index: 1422728 (Python Code)

Max Activating Token Index: 917