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

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

Neuron 458 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4129. Min Range: -1.4129

Max Act: 1.4129. Min Act: -0.0000

Data Index: 1548380 (Python Code)

Max Activating Token Index: 903

Text #1

Max Range: 1.4129. Min Range: -1.4129

Max Act: 1.0848. Min Act: -0.0000

Data Index: 361561 (C4 (Web Text))

Max Activating Token Index: 941

Text #2

Max Range: 1.4129. Min Range: -1.4129

Max Act: 0.9842. Min Act: 0.0000

Data Index: 933148 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 1.4129. Min Range: -1.4129

Max Act: 0.9620. Min Act: -0.0000

Data Index: 1153970 (C4 (Web Text))

Max Activating Token Index: 680

Text #4

Max Range: 1.4129. Min Range: -1.4129

Max Act: 0.9525. Min Act: -0.0000

Data Index: 1423704 (Python Code)

Max Activating Token Index: 768

Text #5

Max Range: 1.4129. Min Range: -1.4129

Max Act: 0.8700. Min Act: -0.0000

Data Index: 1603372 (Python Code)

Max Activating Token Index: 634

Text #6

Max Range: 1.4129. Min Range: -1.4129

Max Act: 0.8473. Min Act: -0.0000

Data Index: 248212 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 1.4129. Min Range: -1.4129

Max Act: 0.7861. Min Act: -0.0000

Data Index: 1525134 (Python Code)

Max Activating Token Index: 413

Text #8

Max Range: 1.4129. Min Range: -1.4129

Max Act: 0.8350. Min Act: -0.0000

Data Index: 1447488 (Python Code)

Max Activating Token Index: 913

Text #9

Max Range: 1.4129. Min Range: -1.4129

Max Act: 0.8373. Min Act: 0.0002

Data Index: 318624 (C4 (Web Text))

Max Activating Token Index: 101

Text #10

Max Range: 1.4129. Min Range: -1.4129

Max Act: 0.8822. Min Act: -0.0000

Data Index: 1439507 (Python Code)

Max Activating Token Index: 186

Text #11

Max Range: 1.4129. Min Range: -1.4129

Max Act: 0.8004. Min Act: -0.0000

Data Index: 1472687 (Python Code)

Max Activating Token Index: 315

Text #12

Max Range: 1.4129. Min Range: -1.4129

Max Act: 0.8658. Min Act: 0.0002

Data Index: 140002 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 1.4129. Min Range: -1.4129

Max Act: 0.8041. Min Act: -0.0000

Data Index: 1503718 (Python Code)

Max Activating Token Index: 764

Text #14

Max Range: 1.4129. Min Range: -1.4129

Max Act: 0.7977. Min Act: -0.0000

Data Index: 1634676 (Python Code)

Max Activating Token Index: 722

Text #15

Max Range: 1.4129. Min Range: -1.4129

Max Act: 0.7935. Min Act: -0.0000

Data Index: 1646069 (Python Code)

Max Activating Token Index: 567

Text #16

Max Range: 1.4129. Min Range: -1.4129

Max Act: 0.7548. Min Act: -0.0000

Data Index: 236286 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 1.4129. Min Range: -1.4129

Max Act: 0.7738. Min Act: -0.0000

Data Index: 143515 (C4 (Web Text))

Max Activating Token Index: 986

Text #18

Max Range: 1.4129. Min Range: -1.4129

Max Act: 0.7741. Min Act: -0.0000

Data Index: 1380816 (Python Code)

Max Activating Token Index: 191

Text #19

Max Range: 1.4129. Min Range: -1.4129

Max Act: 0.7784. Min Act: -0.0000

Data Index: 1614698 (Python Code)

Max Activating Token Index: 873