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

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

Neuron 1620 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: 1.8106. Min Range: -1.8106

Max Act: 1.8106. Min Act: -0.0000

Data Index: 304658 (C4 (Web Text))

Max Activating Token Index: 172

Text #1

Max Range: 1.8106. Min Range: -1.8106

Max Act: 1.6425. Min Act: -0.0000

Data Index: 954496 (C4 (Web Text))

Max Activating Token Index: 635

Text #2

Max Range: 1.8106. Min Range: -1.8106

Max Act: 1.4291. Min Act: -0.0000

Data Index: 1649131 (Python Code)

Max Activating Token Index: 730

Text #3

Max Range: 1.8106. Min Range: -1.8106

Max Act: 1.3515. Min Act: -0.0000

Data Index: 640430 (C4 (Web Text))

Max Activating Token Index: 754

Text #4

Max Range: 1.8106. Min Range: -1.8106

Max Act: 1.2523. Min Act: -0.0000

Data Index: 1315341 (C4 (Web Text))

Max Activating Token Index: 730

Text #5

Max Range: 1.8106. Min Range: -1.8106

Max Act: 1.2116. Min Act: -0.0000

Data Index: 513167 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 1.8106. Min Range: -1.8106

Max Act: 1.1647. Min Act: -0.0000

Data Index: 1201908 (C4 (Web Text))

Max Activating Token Index: 663

Text #7

Max Range: 1.8106. Min Range: -1.8106

Max Act: 1.2014. Min Act: -0.0000

Data Index: 1381405 (Python Code)

Max Activating Token Index: 461

Text #8

Max Range: 1.8106. Min Range: -1.8106

Max Act: 1.1877. Min Act: -0.0000

Data Index: 349023 (C4 (Web Text))

Max Activating Token Index: 934

Text #9

Max Range: 1.8106. Min Range: -1.8106

Max Act: 1.1199. Min Act: -0.0000

Data Index: 183445 (C4 (Web Text))

Max Activating Token Index: 549

Text #10

Max Range: 1.8106. Min Range: -1.8106

Max Act: 1.1823. Min Act: -0.0000

Data Index: 1584771 (Python Code)

Max Activating Token Index: 909

Text #11

Max Range: 1.8106. Min Range: -1.8106

Max Act: 1.1548. Min Act: -0.0000

Data Index: 624560 (C4 (Web Text))

Max Activating Token Index: 57

Text #12

Max Range: 1.8106. Min Range: -1.8106

Max Act: 1.1372. Min Act: -0.0000

Data Index: 1438295 (Python Code)

Max Activating Token Index: 126

Text #13

Max Range: 1.8106. Min Range: -1.8106

Max Act: 1.0671. Min Act: -0.0000

Data Index: 1510237 (Python Code)

Max Activating Token Index: 948

Text #14

Max Range: 1.8106. Min Range: -1.8106

Max Act: 1.1566. Min Act: -0.0000

Data Index: 346656 (C4 (Web Text))

Max Activating Token Index: 459

Text #15

Max Range: 1.8106. Min Range: -1.8106

Max Act: 1.1417. Min Act: -0.0000

Data Index: 1403761 (Python Code)

Max Activating Token Index: 353

Text #16

Max Range: 1.8106. Min Range: -1.8106

Max Act: 1.0077. Min Act: -0.0000

Data Index: 1149495 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 1.8106. Min Range: -1.8106

Max Act: 1.1071. Min Act: -0.0000

Data Index: 492742 (C4 (Web Text))

Max Activating Token Index: 276

Text #18

Max Range: 1.8106. Min Range: -1.8106

Max Act: 1.0299. Min Act: -0.0000

Data Index: 351501 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 1.8106. Min Range: -1.8106

Max Act: 1.0261. Min Act: -0.0000

Data Index: 832132 (C4 (Web Text))

Max Activating Token Index: 842