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

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

Neuron 1216 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4153. Min Range: -0.4153

Max Act: 0.4153. Min Act: -0.0003

Data Index: 1494972 (Python Code)

Max Activating Token Index: 140

Text #1

Max Range: 0.4153. Min Range: -0.4153

Max Act: 0.4054. Min Act: -0.0003

Data Index: 1580542 (Python Code)

Max Activating Token Index: 89

Text #2

Max Range: 0.4153. Min Range: -0.4153

Max Act: 0.3658. Min Act: -0.0002

Data Index: 1382028 (Python Code)

Max Activating Token Index: 674

Text #3

Max Range: 0.4153. Min Range: -0.4153

Max Act: 0.3581. Min Act: -0.0003

Data Index: 1420351 (Python Code)

Max Activating Token Index: 30

Text #4

Max Range: 0.4153. Min Range: -0.4153

Max Act: 0.3316. Min Act: -0.0003

Data Index: 1588549 (Python Code)

Max Activating Token Index: 97

Text #5

Max Range: 0.4153. Min Range: -0.4153

Max Act: 0.3494. Min Act: -0.0002

Data Index: 1639700 (Python Code)

Max Activating Token Index: 101

Text #6

Max Range: 0.4153. Min Range: -0.4153

Max Act: 0.3353. Min Act: -0.0003

Data Index: 1581459 (Python Code)

Max Activating Token Index: 31

Text #7

Max Range: 0.4153. Min Range: -0.4153

Max Act: 0.3450. Min Act: -0.0003

Data Index: 1529261 (Python Code)

Max Activating Token Index: 95

Text #8

Max Range: 0.4153. Min Range: -0.4153

Max Act: 0.3247. Min Act: -0.0003

Data Index: 1545247 (Python Code)

Max Activating Token Index: 141

Text #9

Max Range: 0.4153. Min Range: -0.4153

Max Act: 0.3037. Min Act: -0.0002

Data Index: 1557936 (Python Code)

Max Activating Token Index: 41

Text #10

Max Range: 0.4153. Min Range: -0.4153

Max Act: 0.3226. Min Act: -0.0002

Data Index: 1588888 (Python Code)

Max Activating Token Index: 164

Text #11

Max Range: 0.4153. Min Range: -0.4153

Max Act: 0.3311. Min Act: -0.0003

Data Index: 1463499 (Python Code)

Max Activating Token Index: 598

Text #12

Max Range: 0.4153. Min Range: -0.4153

Max Act: 0.3175. Min Act: -0.0003

Data Index: 1404071 (Python Code)

Max Activating Token Index: 104

Text #13

Max Range: 0.4153. Min Range: -0.4153

Max Act: 0.3233. Min Act: -0.0002

Data Index: 1498287 (Python Code)

Max Activating Token Index: 778

Text #14

Max Range: 0.4153. Min Range: -0.4153

Max Act: 0.2989. Min Act: -0.0003

Data Index: 1441367 (Python Code)

Max Activating Token Index: 36

Text #15

Max Range: 0.4153. Min Range: -0.4153

Max Act: 0.3066. Min Act: -0.0002

Data Index: 1394634 (Python Code)

Max Activating Token Index: 110

Text #16

Max Range: 0.4153. Min Range: -0.4153

Max Act: 0.3025. Min Act: -0.0003

Data Index: 1656793 (Python Code)

Max Activating Token Index: 467

Text #17

Max Range: 0.4153. Min Range: -0.4153

Max Act: 0.3040. Min Act: -0.0003

Data Index: 1618913 (Python Code)

Max Activating Token Index: 52

Text #18

Max Range: 0.4153. Min Range: -0.4153

Max Act: 0.2930. Min Act: -0.0003

Data Index: 1394502 (Python Code)

Max Activating Token Index: 54

Text #19

Max Range: 0.4153. Min Range: -0.4153

Max Act: 0.2937. Min Act: -0.0003

Data Index: 1639625 (Python Code)

Max Activating Token Index: 849