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

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

Neuron 1794 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6364. Min Range: -0.6364

Max Act: 0.6364. Min Act: -0.0000

Data Index: 1560077 (Python Code)

Max Activating Token Index: 534

Text #1

Max Range: 0.6364. Min Range: -0.6364

Max Act: 0.5512. Min Act: -0.0000

Data Index: 1597259 (Python Code)

Max Activating Token Index: 489

Text #2

Max Range: 0.6364. Min Range: -0.6364

Max Act: 0.5630. Min Act: -0.0000

Data Index: 1596761 (Python Code)

Max Activating Token Index: 133

Text #3

Max Range: 0.6364. Min Range: -0.6364

Max Act: 0.5560. Min Act: -0.0000

Data Index: 1640468 (Python Code)

Max Activating Token Index: 141

Text #4

Max Range: 0.6364. Min Range: -0.6364

Max Act: 0.5291. Min Act: -0.0000

Data Index: 1549128 (Python Code)

Max Activating Token Index: 135

Text #5

Max Range: 0.6364. Min Range: -0.6364

Max Act: 0.4910. Min Act: 0.0000

Data Index: 1417028 (Python Code)

Max Activating Token Index: 726

Text #6

Max Range: 0.6364. Min Range: -0.6364

Max Act: 0.4804. Min Act: -0.0000

Data Index: 1603061 (Python Code)

Max Activating Token Index: 33

Text #7

Max Range: 0.6364. Min Range: -0.6364

Max Act: 0.4623. Min Act: -0.0000

Data Index: 966601 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 0.6364. Min Range: -0.6364

Max Act: 0.4636. Min Act: -0.0000

Data Index: 1555040 (Python Code)

Max Activating Token Index: 533

Text #9

Max Range: 0.6364. Min Range: -0.6364

Max Act: 0.4741. Min Act: -0.0000

Data Index: 1467366 (Python Code)

Max Activating Token Index: 993

Text #10

Max Range: 0.6364. Min Range: -0.6364

Max Act: 0.4118. Min Act: -0.0000

Data Index: 1426125 (Python Code)

Max Activating Token Index: 965

Text #11

Max Range: 0.6364. Min Range: -0.6364

Max Act: 0.4448. Min Act: -0.0000

Data Index: 1623115 (Python Code)

Max Activating Token Index: 542

Text #12

Max Range: 0.6364. Min Range: -0.6364

Max Act: 0.3997. Min Act: -0.0000

Data Index: 1510692 (Python Code)

Max Activating Token Index: 45

Text #13

Max Range: 0.6364. Min Range: -0.6364

Max Act: 0.4021. Min Act: 0.0000

Data Index: 1403296 (Python Code)

Max Activating Token Index: 460

Text #14

Max Range: 0.6364. Min Range: -0.6364

Max Act: 0.3757. Min Act: -0.0000

Data Index: 1546731 (Python Code)

Max Activating Token Index: 84

Text #15

Max Range: 0.6364. Min Range: -0.6364

Max Act: 0.3733. Min Act: -0.0000

Data Index: 904080 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 0.6364. Min Range: -0.6364

Max Act: 0.3610. Min Act: -0.0000

Data Index: 1582762 (Python Code)

Max Activating Token Index: 374

Text #17

Max Range: 0.6364. Min Range: -0.6364

Max Act: 0.3799. Min Act: -0.0000

Data Index: 1394942 (Python Code)

Max Activating Token Index: 614

Text #18

Max Range: 0.6364. Min Range: -0.6364

Max Act: 0.3778. Min Act: -0.0000

Data Index: 1470688 (Python Code)

Max Activating Token Index: 117

Text #19

Max Range: 0.6364. Min Range: -0.6364

Max Act: 0.3439. Min Act: -0.0000

Data Index: 1104323 (C4 (Web Text))

Max Activating Token Index: 645