Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3887 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.3870. Min Act: -0.0000

Data Index: 1395320 (Python Code)

Max Activating Token Index: 69

Text #1

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.3720. Min Act: -0.0001

Data Index: 1572613 (Python Code)

Max Activating Token Index: 16

Text #2

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.3596. Min Act: -0.0001

Data Index: 1548801 (Python Code)

Max Activating Token Index: 7

Text #3

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.3391. Min Act: -0.0001

Data Index: 1506335 (Python Code)

Max Activating Token Index: 30

Text #4

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.3490. Min Act: -0.0001

Data Index: 1371525 (Python Code)

Max Activating Token Index: 52

Text #5

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.3489. Min Act: -0.0001

Data Index: 1416291 (Python Code)

Max Activating Token Index: 103

Text #6

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.3432. Min Act: -0.0001

Data Index: 1641643 (Python Code)

Max Activating Token Index: 21

Text #7

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.3392. Min Act: -0.0000

Data Index: 1449664 (Python Code)

Max Activating Token Index: 97

Text #8

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.3374. Min Act: -0.0001

Data Index: 1569170 (Python Code)

Max Activating Token Index: 120

Text #9

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.3245. Min Act: -0.0001

Data Index: 1569731 (Python Code)

Max Activating Token Index: 14

Text #10

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.3341. Min Act: -0.0001

Data Index: 1463420 (Python Code)

Max Activating Token Index: 11

Text #11

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.3334. Min Act: -0.0001

Data Index: 1597214 (Python Code)

Max Activating Token Index: 37

Text #12

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.3260. Min Act: -0.0001

Data Index: 1519338 (Python Code)

Max Activating Token Index: 32

Text #13

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.3109. Min Act: -0.0001

Data Index: 1603798 (Python Code)

Max Activating Token Index: 54

Text #14

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.3170. Min Act: -0.0001

Data Index: 1402441 (Python Code)

Max Activating Token Index: 25

Text #15

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.3166. Min Act: -0.0000

Data Index: 1421892 (Python Code)

Max Activating Token Index: 77

Text #16

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.3051. Min Act: -0.0001

Data Index: 1625034 (Python Code)

Max Activating Token Index: 130

Text #17

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.3044. Min Act: -0.0001

Data Index: 1589688 (Python Code)

Max Activating Token Index: 17

Text #18

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.3131. Min Act: -0.0001

Data Index: 1587526 (Python Code)

Max Activating Token Index: 26

Text #19

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.3013. Min Act: -0.0001

Data Index: 1495073 (Python Code)

Max Activating Token Index: 16