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

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

Neuron 1112 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: 2.1127. Min Range: -2.1127

Max Act: 2.1127. Min Act: -0.0000

Data Index: 1428236 (Python Code)

Max Activating Token Index: 79

Text #1

Max Range: 2.1127. Min Range: -2.1127

Max Act: 1.7942. Min Act: -0.0000

Data Index: 1491032 (Python Code)

Max Activating Token Index: 114

Text #2

Max Range: 2.1127. Min Range: -2.1127

Max Act: 1.7715. Min Act: -0.0000

Data Index: 367638 (C4 (Web Text))

Max Activating Token Index: 688

Text #3

Max Range: 2.1127. Min Range: -2.1127

Max Act: 1.7479. Min Act: -0.0000

Data Index: 47262 (C4 (Web Text))

Max Activating Token Index: 543

Text #4

Max Range: 2.1127. Min Range: -2.1127

Max Act: 1.7104. Min Act: -0.0000

Data Index: 1528540 (Python Code)

Max Activating Token Index: 162

Text #5

Max Range: 2.1127. Min Range: -2.1127

Max Act: 1.5752. Min Act: -0.0000

Data Index: 638419 (C4 (Web Text))

Max Activating Token Index: 781

Text #6

Max Range: 2.1127. Min Range: -2.1127

Max Act: 1.7761. Min Act: -0.0000

Data Index: 336389 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 2.1127. Min Range: -2.1127

Max Act: 1.7613. Min Act: -0.0000

Data Index: 212923 (C4 (Web Text))

Max Activating Token Index: 342

Text #8

Max Range: 2.1127. Min Range: -2.1127

Max Act: 1.6267. Min Act: -0.0000

Data Index: 1539796 (Python Code)

Max Activating Token Index: 128

Text #9

Max Range: 2.1127. Min Range: -2.1127

Max Act: 1.6270. Min Act: -0.0000

Data Index: 438806 (C4 (Web Text))

Max Activating Token Index: 804

Text #10

Max Range: 2.1127. Min Range: -2.1127

Max Act: 1.6181. Min Act: -0.0000

Data Index: 1645813 (Python Code)

Max Activating Token Index: 195

Text #11

Max Range: 2.1127. Min Range: -2.1127

Max Act: 1.6065. Min Act: -0.0000

Data Index: 1230436 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 2.1127. Min Range: -2.1127

Max Act: 1.5923. Min Act: -0.0000

Data Index: 67700 (C4 (Web Text))

Max Activating Token Index: 965

Text #13

Max Range: 2.1127. Min Range: -2.1127

Max Act: 1.5867. Min Act: -0.0000

Data Index: 1497391 (Python Code)

Max Activating Token Index: 303

Text #14

Max Range: 2.1127. Min Range: -2.1127

Max Act: 1.5729. Min Act: -0.0000

Data Index: 355425 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 2.1127. Min Range: -2.1127

Max Act: 1.5709. Min Act: -0.0000

Data Index: 1443271 (Python Code)

Max Activating Token Index: 255

Text #16

Max Range: 2.1127. Min Range: -2.1127

Max Act: 1.5545. Min Act: -0.0000

Data Index: 1452780 (Python Code)

Max Activating Token Index: 535

Text #17

Max Range: 2.1127. Min Range: -2.1127

Max Act: 1.6399. Min Act: -0.0000

Data Index: 691948 (C4 (Web Text))

Max Activating Token Index: 782

Text #18

Max Range: 2.1127. Min Range: -2.1127

Max Act: 1.5323. Min Act: -0.0000

Data Index: 831221 (C4 (Web Text))

Max Activating Token Index: 694

Text #19

Max Range: 2.1127. Min Range: -2.1127

Max Act: 1.4503. Min Act: -0.0000

Data Index: 637436 (C4 (Web Text))

Max Activating Token Index: 270