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

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

Neuron 4794 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3888. Min Act: -0.0000

Data Index: 1484551 (Python Code)

Max Activating Token Index: 68

Text #1

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3975. Min Act: -0.0000

Data Index: 1576172 (Python Code)

Max Activating Token Index: 201

Text #2

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3730. Min Act: -0.0000

Data Index: 1377318 (Python Code)

Max Activating Token Index: 86

Text #3

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3368. Min Act: -0.0000

Data Index: 1590377 (Python Code)

Max Activating Token Index: 320

Text #4

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3342. Min Act: -0.0000

Data Index: 1463239 (Python Code)

Max Activating Token Index: 31

Text #5

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3303. Min Act: -0.0000

Data Index: 1620045 (Python Code)

Max Activating Token Index: 174

Text #6

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3407. Min Act: -0.0000

Data Index: 1536607 (Python Code)

Max Activating Token Index: 265

Text #7

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3346. Min Act: -0.0000

Data Index: 1534047 (Python Code)

Max Activating Token Index: 30

Text #8

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3346. Min Act: -0.0000

Data Index: 1549421 (Python Code)

Max Activating Token Index: 30

Text #9

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3141. Min Act: -0.0000

Data Index: 1557049 (Python Code)

Max Activating Token Index: 49

Text #10

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3342. Min Act: -0.0000

Data Index: 1634841 (Python Code)

Max Activating Token Index: 183

Text #11

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3204. Min Act: -0.0000

Data Index: 1556987 (Python Code)

Max Activating Token Index: 252

Text #12

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3539. Min Act: -0.0000

Data Index: 1399814 (Python Code)

Max Activating Token Index: 187

Text #13

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3213. Min Act: -0.0000

Data Index: 1460225 (Python Code)

Max Activating Token Index: 39

Text #14

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3213. Min Act: -0.0000

Data Index: 1510265 (Python Code)

Max Activating Token Index: 39

Text #15

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3316. Min Act: -0.0000

Data Index: 1506477 (Python Code)

Max Activating Token Index: 425

Text #16

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3298. Min Act: -0.0000

Data Index: 1581934 (Python Code)

Max Activating Token Index: 480

Text #17

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3301. Min Act: -0.0000

Data Index: 1444079 (Python Code)

Max Activating Token Index: 184

Text #18

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3165. Min Act: -0.0000

Data Index: 1494957 (Python Code)

Max Activating Token Index: 56

Text #19

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3313. Min Act: -0.0000

Data Index: 1563142 (Python Code)

Max Activating Token Index: 26