Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3660 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.6890. Min Act: -0.0000

Data Index: 1615833 (Python Code)

Max Activating Token Index: 522

Text #1

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.6826. Min Act: -0.0001

Data Index: 1433509 (Python Code)

Max Activating Token Index: 735

Text #2

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.5996. Min Act: -0.0000

Data Index: 1515909 (Python Code)

Max Activating Token Index: 160

Text #3

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.5772. Min Act: -0.0001

Data Index: 1385063 (Python Code)

Max Activating Token Index: 207

Text #4

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.5818. Min Act: -0.0001

Data Index: 1400589 (Python Code)

Max Activating Token Index: 850

Text #5

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.5366. Min Act: -0.0001

Data Index: 1653067 (Python Code)

Max Activating Token Index: 397

Text #6

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.5684. Min Act: -0.0000

Data Index: 354993 (C4 (Web Text))

Max Activating Token Index: 610

Text #7

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.5246. Min Act: -0.0001

Data Index: 1586757 (Python Code)

Max Activating Token Index: 542

Text #8

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.5064. Min Act: -0.0000

Data Index: 1642317 (Python Code)

Max Activating Token Index: 634

Text #9

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.4970. Min Act: -0.0001

Data Index: 1611395 (Python Code)

Max Activating Token Index: 941

Text #10

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.5227. Min Act: -0.0001

Data Index: 1596315 (Python Code)

Max Activating Token Index: 48

Text #11

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.5026. Min Act: -0.0001

Data Index: 1525539 (Python Code)

Max Activating Token Index: 327

Text #12

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.4550. Min Act: -0.0000

Data Index: 1473299 (Python Code)

Max Activating Token Index: 82

Text #13

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.4696. Min Act: -0.0000

Data Index: 1374391 (Python Code)

Max Activating Token Index: 817

Text #14

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.4428. Min Act: -0.0001

Data Index: 1495916 (Python Code)

Max Activating Token Index: 342

Text #15

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.4578. Min Act: -0.0001

Data Index: 1469322 (Python Code)

Max Activating Token Index: 76

Text #16

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.4158. Min Act: -0.0000

Data Index: 1572777 (Python Code)

Max Activating Token Index: 603

Text #17

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.4588. Min Act: -0.0001

Data Index: 1652899 (Python Code)

Max Activating Token Index: 962

Text #18

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.4486. Min Act: 0.0000

Data Index: 1418862 (Python Code)

Max Activating Token Index: 868

Text #19

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.4471. Min Act: -0.0000

Data Index: 1471437 (Python Code)

Max Activating Token Index: 891