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

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

Neuron 3106 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3215. Min Range: -1.3215

Max Act: 1.3215. Min Act: -0.0000

Data Index: 1495849 (Python Code)

Max Activating Token Index: 9

Text #1

Max Range: 1.3215. Min Range: -1.3215

Max Act: 1.3100. Min Act: -0.0000

Data Index: 1596080 (Python Code)

Max Activating Token Index: 20

Text #2

Max Range: 1.3215. Min Range: -1.3215

Max Act: 1.3074. Min Act: -0.0000

Data Index: 1359959 (Python Code)

Max Activating Token Index: 428

Text #3

Max Range: 1.3215. Min Range: -1.3215

Max Act: 1.2735. Min Act: -0.0000

Data Index: 1586811 (Python Code)

Max Activating Token Index: 53

Text #4

Max Range: 1.3215. Min Range: -1.3215

Max Act: 1.2630. Min Act: -0.0000

Data Index: 1488543 (Python Code)

Max Activating Token Index: 281

Text #5

Max Range: 1.3215. Min Range: -1.3215

Max Act: 1.2496. Min Act: -0.0000

Data Index: 1504343 (Python Code)

Max Activating Token Index: 957

Text #6

Max Range: 1.3215. Min Range: -1.3215

Max Act: 1.2872. Min Act: -0.0000

Data Index: 1566856 (Python Code)

Max Activating Token Index: 106

Text #7

Max Range: 1.3215. Min Range: -1.3215

Max Act: 1.2882. Min Act: -0.0000

Data Index: 1403328 (Python Code)

Max Activating Token Index: 189

Text #8

Max Range: 1.3215. Min Range: -1.3215

Max Act: 1.1885. Min Act: -0.0000

Data Index: 1656910 (Python Code)

Max Activating Token Index: 354

Text #9

Max Range: 1.3215. Min Range: -1.3215

Max Act: 1.1931. Min Act: -0.0000

Data Index: 1400309 (Python Code)

Max Activating Token Index: 154

Text #10

Max Range: 1.3215. Min Range: -1.3215

Max Act: 1.1336. Min Act: -0.0000

Data Index: 1367123 (Python Code)

Max Activating Token Index: 363

Text #11

Max Range: 1.3215. Min Range: -1.3215

Max Act: 1.2052. Min Act: -0.0000

Data Index: 1628028 (Python Code)

Max Activating Token Index: 214

Text #12

Max Range: 1.3215. Min Range: -1.3215

Max Act: 1.1640. Min Act: -0.0000

Data Index: 1498913 (Python Code)

Max Activating Token Index: 66

Text #13

Max Range: 1.3215. Min Range: -1.3215

Max Act: 1.1941. Min Act: -0.0000

Data Index: 1600704 (Python Code)

Max Activating Token Index: 255

Text #14

Max Range: 1.3215. Min Range: -1.3215

Max Act: 1.1536. Min Act: -0.0000

Data Index: 1397647 (Python Code)

Max Activating Token Index: 114

Text #15

Max Range: 1.3215. Min Range: -1.3215

Max Act: 1.1888. Min Act: -0.0000

Data Index: 1432677 (Python Code)

Max Activating Token Index: 27

Text #16

Max Range: 1.3215. Min Range: -1.3215

Max Act: 1.2221. Min Act: -0.0000

Data Index: 1558720 (Python Code)

Max Activating Token Index: 19

Text #17

Max Range: 1.3215. Min Range: -1.3215

Max Act: 1.2187. Min Act: -0.0000

Data Index: 1607158 (Python Code)

Max Activating Token Index: 182

Text #18

Max Range: 1.3215. Min Range: -1.3215

Max Act: 1.1772. Min Act: -0.0000

Data Index: 1474688 (Python Code)

Max Activating Token Index: 21

Text #19

Max Range: 1.3215. Min Range: -1.3215

Max Act: 1.1741. Min Act: -0.0000

Data Index: 1647276 (Python Code)

Max Activating Token Index: 140