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

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

Neuron 1169 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7929. Min Range: -2.7929

Max Act: 2.6688. Min Act: -0.0001

Data Index: 1448293 (Python Code)

Max Activating Token Index: 36

Text #1

Max Range: 2.7929. Min Range: -2.7929

Max Act: 2.7929. Min Act: -0.0000

Data Index: 1639669 (Python Code)

Max Activating Token Index: 43

Text #2

Max Range: 2.7929. Min Range: -2.7929

Max Act: 2.6640. Min Act: -0.0000

Data Index: 1602021 (Python Code)

Max Activating Token Index: 43

Text #3

Max Range: 2.7929. Min Range: -2.7929

Max Act: 2.6077. Min Act: -0.0001

Data Index: 1384728 (Python Code)

Max Activating Token Index: 41

Text #4

Max Range: 2.7929. Min Range: -2.7929

Max Act: 2.3485. Min Act: -0.0001

Data Index: 1416562 (Python Code)

Max Activating Token Index: 50

Text #5

Max Range: 2.7929. Min Range: -2.7929

Max Act: 2.4691. Min Act: -0.0001

Data Index: 1602333 (Python Code)

Max Activating Token Index: 10

Text #6

Max Range: 2.7929. Min Range: -2.7929

Max Act: 2.3343. Min Act: -0.0001

Data Index: 1523942 (Python Code)

Max Activating Token Index: 6

Text #7

Max Range: 2.7929. Min Range: -2.7929

Max Act: 2.4180. Min Act: -0.0000

Data Index: 1590648 (Python Code)

Max Activating Token Index: 45

Text #8

Max Range: 2.7929. Min Range: -2.7929

Max Act: 2.3930. Min Act: -0.0001

Data Index: 1404269 (Python Code)

Max Activating Token Index: 15

Text #9

Max Range: 2.7929. Min Range: -2.7929

Max Act: 2.3873. Min Act: -0.0001

Data Index: 1391734 (Python Code)

Max Activating Token Index: 93

Text #10

Max Range: 2.7929. Min Range: -2.7929

Max Act: 2.2561. Min Act: -0.0001

Data Index: 1563887 (Python Code)

Max Activating Token Index: 27

Text #11

Max Range: 2.7929. Min Range: -2.7929

Max Act: 2.3337. Min Act: -0.0001

Data Index: 1471760 (Python Code)

Max Activating Token Index: 6

Text #12

Max Range: 2.7929. Min Range: -2.7929

Max Act: 2.3369. Min Act: -0.0000

Data Index: 1434122 (Python Code)

Max Activating Token Index: 4

Text #13

Max Range: 2.7929. Min Range: -2.7929

Max Act: 2.3369. Min Act: -0.0001

Data Index: 1524744 (Python Code)

Max Activating Token Index: 4

Text #14

Max Range: 2.7929. Min Range: -2.7929

Max Act: 2.3369. Min Act: -0.0001

Data Index: 1652061 (Python Code)

Max Activating Token Index: 4

Text #15

Max Range: 2.7929. Min Range: -2.7929

Max Act: 2.3369. Min Act: -0.0000

Data Index: 1604776 (Python Code)

Max Activating Token Index: 4

Text #16

Max Range: 2.7929. Min Range: -2.7929

Max Act: 2.3369. Min Act: -0.0000

Data Index: 1375611 (Python Code)

Max Activating Token Index: 4

Text #17

Max Range: 2.7929. Min Range: -2.7929

Max Act: 2.3291. Min Act: -0.0001

Data Index: 1465926 (Python Code)

Max Activating Token Index: 7

Text #18

Max Range: 2.7929. Min Range: -2.7929

Max Act: 2.3251. Min Act: -0.0001

Data Index: 1541206 (Python Code)

Max Activating Token Index: 23

Text #19

Max Range: 2.7929. Min Range: -2.7929

Max Act: 2.2017. Min Act: -0.0001

Data Index: 1482369 (Python Code)

Max Activating Token Index: 43