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

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

Neuron 4978 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7883. Min Range: -1.7883

Max Act: 1.7883. Min Act: -0.0000

Data Index: 1499644 (Python Code)

Max Activating Token Index: 92

Text #1

Max Range: 1.7883. Min Range: -1.7883

Max Act: 1.7009. Min Act: -0.0000

Data Index: 1064095 (C4 (Web Text))

Max Activating Token Index: 258

Text #2

Max Range: 1.7883. Min Range: -1.7883

Max Act: 1.4673. Min Act: -0.0000

Data Index: 1556242 (Python Code)

Max Activating Token Index: 83

Text #3

Max Range: 1.7883. Min Range: -1.7883

Max Act: 1.3806. Min Act: -0.0000

Data Index: 1485292 (Python Code)

Max Activating Token Index: 122

Text #4

Max Range: 1.7883. Min Range: -1.7883

Max Act: 1.4158. Min Act: -0.0000

Data Index: 1274433 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 1.7883. Min Range: -1.7883

Max Act: 1.3609. Min Act: -0.0000

Data Index: 1411532 (Python Code)

Max Activating Token Index: 17

Text #6

Max Range: 1.7883. Min Range: -1.7883

Max Act: 1.3191. Min Act: -0.0000

Data Index: 1396416 (Python Code)

Max Activating Token Index: 46

Text #7

Max Range: 1.7883. Min Range: -1.7883

Max Act: 1.2963. Min Act: -0.0000

Data Index: 1584290 (Python Code)

Max Activating Token Index: 44

Text #8

Max Range: 1.7883. Min Range: -1.7883

Max Act: 1.3234. Min Act: -0.0000

Data Index: 1606988 (Python Code)

Max Activating Token Index: 30

Text #9

Max Range: 1.7883. Min Range: -1.7883

Max Act: 1.2178. Min Act: -0.0000

Data Index: 1498552 (Python Code)

Max Activating Token Index: 35

Text #10

Max Range: 1.7883. Min Range: -1.7883

Max Act: 1.2807. Min Act: -0.0000

Data Index: 1514474 (Python Code)

Max Activating Token Index: 54

Text #11

Max Range: 1.7883. Min Range: -1.7883

Max Act: 1.2562. Min Act: -0.0000

Data Index: 1479646 (Python Code)

Max Activating Token Index: 61

Text #12

Max Range: 1.7883. Min Range: -1.7883

Max Act: 1.2488. Min Act: -0.0000

Data Index: 1567563 (Python Code)

Max Activating Token Index: 897

Text #13

Max Range: 1.7883. Min Range: -1.7883

Max Act: 1.2868. Min Act: -0.0000

Data Index: 1521671 (Python Code)

Max Activating Token Index: 306

Text #14

Max Range: 1.7883. Min Range: -1.7883

Max Act: 1.3179. Min Act: -0.0000

Data Index: 1517958 (Python Code)

Max Activating Token Index: 712

Text #15

Max Range: 1.7883. Min Range: -1.7883

Max Act: 1.2247. Min Act: -0.0000

Data Index: 1607228 (Python Code)

Max Activating Token Index: 178

Text #16

Max Range: 1.7883. Min Range: -1.7883

Max Act: 1.2127. Min Act: -0.0000

Data Index: 1574924 (Python Code)

Max Activating Token Index: 1019

Text #17

Max Range: 1.7883. Min Range: -1.7883

Max Act: 1.2216. Min Act: -0.0000

Data Index: 1626928 (Python Code)

Max Activating Token Index: 61

Text #18

Max Range: 1.7883. Min Range: -1.7883

Max Act: 1.2450. Min Act: -0.0000

Data Index: 1392066 (Python Code)

Max Activating Token Index: 46

Text #19

Max Range: 1.7883. Min Range: -1.7883

Max Act: 1.2882. Min Act: -0.0000

Data Index: 1628336 (Python Code)

Max Activating Token Index: 178