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

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

Neuron 4645 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: 0.3671. Min Range: -0.3671

Max Act: 0.3671. Min Act: -0.0001

Data Index: 610671 (C4 (Web Text))

Max Activating Token Index: 656

Text #1

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.3166. Min Act: -0.0000

Data Index: 1397634 (Python Code)

Max Activating Token Index: 28

Text #2

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2896. Min Act: -0.0001

Data Index: 1152131 (C4 (Web Text))

Max Activating Token Index: 503

Text #3

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.3364. Min Act: -0.0000

Data Index: 1371025 (Python Code)

Max Activating Token Index: 252

Text #4

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.3141. Min Act: -0.0001

Data Index: 435906 (C4 (Web Text))

Max Activating Token Index: 676

Text #5

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2676. Min Act: -0.0001

Data Index: 1347860 (C4 (Web Text))

Max Activating Token Index: 678

Text #6

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2973. Min Act: -0.0000

Data Index: 1434898 (Python Code)

Max Activating Token Index: 336

Text #7

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2875. Min Act: -0.0000

Data Index: 1424432 (Python Code)

Max Activating Token Index: 941

Text #8

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2931. Min Act: -0.0000

Data Index: 1584419 (Python Code)

Max Activating Token Index: 317

Text #9

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2875. Min Act: -0.0000

Data Index: 487365 (C4 (Web Text))

Max Activating Token Index: 987

Text #10

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2645. Min Act: -0.0000

Data Index: 1421200 (Python Code)

Max Activating Token Index: 925

Text #11

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2548. Min Act: -0.0000

Data Index: 1368393 (Python Code)

Max Activating Token Index: 377

Text #12

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2581. Min Act: -0.0000

Data Index: 1513587 (Python Code)

Max Activating Token Index: 981

Text #13

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2697. Min Act: -0.0001

Data Index: 334925 (C4 (Web Text))

Max Activating Token Index: 426

Text #14

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2509. Min Act: -0.0000

Data Index: 1391857 (Python Code)

Max Activating Token Index: 75

Text #15

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2570. Min Act: -0.0000

Data Index: 1588699 (Python Code)

Max Activating Token Index: 34

Text #16

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2684. Min Act: -0.0000

Data Index: 1547019 (Python Code)

Max Activating Token Index: 722

Text #17

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2512. Min Act: -0.0000

Data Index: 1462512 (Python Code)

Max Activating Token Index: 53

Text #18

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2442. Min Act: -0.0000

Data Index: 1560494 (Python Code)

Max Activating Token Index: 617

Text #19

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2278. Min Act: -0.0000

Data Index: 1429466 (Python Code)

Max Activating Token Index: 959