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

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

Neuron 3705 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: 7.4674. Min Range: -7.4674

Max Act: 7.4674. Min Act: -0.0000

Data Index: 174587 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 7.4674. Min Range: -7.4674

Max Act: 7.0782. Min Act: -0.0000

Data Index: 1011918 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 7.4674. Min Range: -7.4674

Max Act: 7.0052. Min Act: -0.0000

Data Index: 1058551 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 7.4674. Min Range: -7.4674

Max Act: 6.0576. Min Act: -0.0000

Data Index: 1298804 (C4 (Web Text))

Max Activating Token Index: 18

Text #4

Max Range: 7.4674. Min Range: -7.4674

Max Act: 6.0176. Min Act: -0.0000

Data Index: 884712 (C4 (Web Text))

Max Activating Token Index: 890

Text #5

Max Range: 7.4674. Min Range: -7.4674

Max Act: 6.3468. Min Act: -0.0000

Data Index: 561755 (C4 (Web Text))

Max Activating Token Index: 926

Text #6

Max Range: 7.4674. Min Range: -7.4674

Max Act: 6.0393. Min Act: -0.0000

Data Index: 1306886 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 7.4674. Min Range: -7.4674

Max Act: 6.0335. Min Act: -0.0000

Data Index: 919396 (C4 (Web Text))

Max Activating Token Index: 813

Text #8

Max Range: 7.4674. Min Range: -7.4674

Max Act: 6.1661. Min Act: -0.0000

Data Index: 480411 (C4 (Web Text))

Max Activating Token Index: 826

Text #9

Max Range: 7.4674. Min Range: -7.4674

Max Act: 5.9659. Min Act: -0.0000

Data Index: 785065 (C4 (Web Text))

Max Activating Token Index: 578

Text #10

Max Range: 7.4674. Min Range: -7.4674

Max Act: 5.9176. Min Act: -0.0000

Data Index: 331065 (C4 (Web Text))

Max Activating Token Index: 24

Text #11

Max Range: 7.4674. Min Range: -7.4674

Max Act: 5.8228. Min Act: -0.0000

Data Index: 230995 (C4 (Web Text))

Max Activating Token Index: 559

Text #12

Max Range: 7.4674. Min Range: -7.4674

Max Act: 5.8113. Min Act: -0.0000

Data Index: 869985 (C4 (Web Text))

Max Activating Token Index: 749

Text #13

Max Range: 7.4674. Min Range: -7.4674

Max Act: 5.6224. Min Act: -0.0000

Data Index: 631533 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 7.4674. Min Range: -7.4674

Max Act: 5.8000. Min Act: -0.0000

Data Index: 863351 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 7.4674. Min Range: -7.4674

Max Act: 6.1884. Min Act: -0.0000

Data Index: 1330578 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 7.4674. Min Range: -7.4674

Max Act: 5.7829. Min Act: -0.0000

Data Index: 1291727 (C4 (Web Text))

Max Activating Token Index: 964

Text #17

Max Range: 7.4674. Min Range: -7.4674

Max Act: 5.8009. Min Act: -0.0000

Data Index: 584403 (C4 (Web Text))

Max Activating Token Index: 900

Text #18

Max Range: 7.4674. Min Range: -7.4674

Max Act: 5.7757. Min Act: -0.0000

Data Index: 1235210 (C4 (Web Text))

Max Activating Token Index: 823

Text #19

Max Range: 7.4674. Min Range: -7.4674

Max Act: 5.5966. Min Act: -0.0000

Data Index: 670166 (C4 (Web Text))

Max Activating Token Index: 873