Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2969 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.7394. Min Act: -0.0000

Data Index: 1527582 (Python Code)

Max Activating Token Index: 737

Text #1

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.7636. Min Act: -0.0000

Data Index: 1544996 (Python Code)

Max Activating Token Index: 83

Text #2

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.6546. Min Act: -0.0000

Data Index: 1411708 (Python Code)

Max Activating Token Index: 232

Text #3

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.6284. Min Act: -0.0000

Data Index: 1560315 (Python Code)

Max Activating Token Index: 34

Text #4

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.5864. Min Act: 0.0000

Data Index: 415673 (C4 (Web Text))

Max Activating Token Index: 892

Text #5

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.6281. Min Act: -0.0000

Data Index: 1595166 (Python Code)

Max Activating Token Index: 791

Text #6

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.6007. Min Act: -0.0000

Data Index: 1523102 (Python Code)

Max Activating Token Index: 434

Text #7

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.6361. Min Act: -0.0000

Data Index: 1431937 (Python Code)

Max Activating Token Index: 690

Text #8

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.5092. Min Act: -0.0000

Data Index: 1412480 (Python Code)

Max Activating Token Index: 758

Text #9

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.5332. Min Act: -0.0000

Data Index: 1419812 (Python Code)

Max Activating Token Index: 109

Text #10

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.5465. Min Act: -0.0000

Data Index: 1373932 (Python Code)

Max Activating Token Index: 989

Text #11

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.5058. Min Act: 0.0000

Data Index: 1376906 (Python Code)

Max Activating Token Index: 924

Text #12

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.5294. Min Act: -0.0000

Data Index: 1375185 (Python Code)

Max Activating Token Index: 387

Text #13

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.5158. Min Act: 0.0001

Data Index: 1440429 (Python Code)

Max Activating Token Index: 602

Text #14

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.5232. Min Act: -0.0000

Data Index: 1583267 (Python Code)

Max Activating Token Index: 169

Text #15

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.5119. Min Act: -0.0000

Data Index: 1548633 (Python Code)

Max Activating Token Index: 629

Text #16

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.5175. Min Act: -0.0000

Data Index: 1421624 (Python Code)

Max Activating Token Index: 228

Text #17

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.4943. Min Act: -0.0000

Data Index: 1384002 (Python Code)

Max Activating Token Index: 547

Text #18

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.4939. Min Act: 0.0000

Data Index: 1434936 (Python Code)

Max Activating Token Index: 113

Text #19

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.4528. Min Act: -0.0000

Data Index: 1551823 (Python Code)

Max Activating Token Index: 378