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

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

Neuron 483 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: 2.9877. Min Range: -2.9877

Max Act: 2.9877. Min Act: -0.0000

Data Index: 1538582 (Python Code)

Max Activating Token Index: 65

Text #1

Max Range: 2.9877. Min Range: -2.9877

Max Act: 2.6454. Min Act: -0.0000

Data Index: 1362212 (Python Code)

Max Activating Token Index: 659

Text #2

Max Range: 2.9877. Min Range: -2.9877

Max Act: 2.7406. Min Act: -0.0000

Data Index: 1435489 (Python Code)

Max Activating Token Index: 916

Text #3

Max Range: 2.9877. Min Range: -2.9877

Max Act: 2.5252. Min Act: -0.0000

Data Index: 372925 (C4 (Web Text))

Max Activating Token Index: 221

Text #4

Max Range: 2.9877. Min Range: -2.9877

Max Act: 2.1910. Min Act: -0.0000

Data Index: 1078118 (C4 (Web Text))

Max Activating Token Index: 950

Text #5

Max Range: 2.9877. Min Range: -2.9877

Max Act: 2.4159. Min Act: -0.0000

Data Index: 1636090 (Python Code)

Max Activating Token Index: 612

Text #6

Max Range: 2.9877. Min Range: -2.9877

Max Act: 2.3636. Min Act: -0.0000

Data Index: 1392670 (Python Code)

Max Activating Token Index: 6

Text #7

Max Range: 2.9877. Min Range: -2.9877

Max Act: 2.2922. Min Act: -0.0000

Data Index: 507440 (C4 (Web Text))

Max Activating Token Index: 53

Text #8

Max Range: 2.9877. Min Range: -2.9877

Max Act: 2.3777. Min Act: -0.0000

Data Index: 384843 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 2.9877. Min Range: -2.9877

Max Act: 2.1379. Min Act: -0.0000

Data Index: 1448395 (Python Code)

Max Activating Token Index: 940

Text #10

Max Range: 2.9877. Min Range: -2.9877

Max Act: 2.2634. Min Act: -0.0000

Data Index: 1032742 (C4 (Web Text))

Max Activating Token Index: 528

Text #11

Max Range: 2.9877. Min Range: -2.9877

Max Act: 1.9987. Min Act: -0.0000

Data Index: 1453591 (Python Code)

Max Activating Token Index: 386

Text #12

Max Range: 2.9877. Min Range: -2.9877

Max Act: 2.0802. Min Act: -0.0000

Data Index: 386925 (C4 (Web Text))

Max Activating Token Index: 641

Text #13

Max Range: 2.9877. Min Range: -2.9877

Max Act: 2.1773. Min Act: -0.0000

Data Index: 843976 (C4 (Web Text))

Max Activating Token Index: 484

Text #14

Max Range: 2.9877. Min Range: -2.9877

Max Act: 2.0470. Min Act: -0.0000

Data Index: 1472765 (Python Code)

Max Activating Token Index: 27

Text #15

Max Range: 2.9877. Min Range: -2.9877

Max Act: 2.1560. Min Act: -0.0000

Data Index: 1386851 (Python Code)

Max Activating Token Index: 765

Text #16

Max Range: 2.9877. Min Range: -2.9877

Max Act: 2.1501. Min Act: -0.0000

Data Index: 1484610 (Python Code)

Max Activating Token Index: 339

Text #17

Max Range: 2.9877. Min Range: -2.9877

Max Act: 2.0418. Min Act: -0.0000

Data Index: 1428571 (Python Code)

Max Activating Token Index: 823

Text #18

Max Range: 2.9877. Min Range: -2.9877

Max Act: 2.1619. Min Act: -0.0000

Data Index: 1404745 (Python Code)

Max Activating Token Index: 300

Text #19

Max Range: 2.9877. Min Range: -2.9877

Max Act: 2.1236. Min Act: -0.0000

Data Index: 1511411 (Python Code)

Max Activating Token Index: 392