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

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

Neuron 4728 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.7626. Min Act: -0.0000

Data Index: 1392595 (Python Code)

Max Activating Token Index: 899

Text #1

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.7193. Min Act: -0.0000

Data Index: 455717 (C4 (Web Text))

Max Activating Token Index: 923

Text #2

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.6811. Min Act: -0.0000

Data Index: 1472800 (Python Code)

Max Activating Token Index: 858

Text #3

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.6151. Min Act: -0.0000

Data Index: 1483729 (Python Code)

Max Activating Token Index: 156

Text #4

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.6214. Min Act: -0.0000

Data Index: 1515207 (Python Code)

Max Activating Token Index: 987

Text #5

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5850. Min Act: -0.0000

Data Index: 505157 (C4 (Web Text))

Max Activating Token Index: 717

Text #6

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5982. Min Act: -0.0000

Data Index: 1420442 (Python Code)

Max Activating Token Index: 203

Text #7

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5916. Min Act: -0.0000

Data Index: 1507124 (Python Code)

Max Activating Token Index: 389

Text #8

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5358. Min Act: -0.0000

Data Index: 1511314 (Python Code)

Max Activating Token Index: 54

Text #9

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5273. Min Act: -0.0000

Data Index: 1558968 (Python Code)

Max Activating Token Index: 362

Text #10

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.4859. Min Act: -0.0000

Data Index: 1454841 (Python Code)

Max Activating Token Index: 120

Text #11

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5152. Min Act: -0.0000

Data Index: 1311166 (C4 (Web Text))

Max Activating Token Index: 561

Text #12

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5016. Min Act: -0.0000

Data Index: 1371431 (Python Code)

Max Activating Token Index: 748

Text #13

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5121. Min Act: -0.0000

Data Index: 1486482 (Python Code)

Max Activating Token Index: 373

Text #14

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5092. Min Act: -0.0000

Data Index: 1446170 (Python Code)

Max Activating Token Index: 134

Text #15

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.4916. Min Act: -0.0000

Data Index: 1421398 (Python Code)

Max Activating Token Index: 510

Text #16

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5090. Min Act: -0.0000

Data Index: 1487320 (Python Code)

Max Activating Token Index: 545

Text #17

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5055. Min Act: -0.0000

Data Index: 1380574 (Python Code)

Max Activating Token Index: 814

Text #18

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5201. Min Act: -0.0000

Data Index: 1456605 (Python Code)

Max Activating Token Index: 58

Text #19

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.4757. Min Act: -0.0000

Data Index: 854648 (C4 (Web Text))

Max Activating Token Index: 308