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

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

Neuron 11 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3156. Min Range: -1.3156

Max Act: 1.1428. Min Act: -0.0000

Data Index: 1639766 (Python Code)

Max Activating Token Index: 212

Text #1

Max Range: 1.3156. Min Range: -1.3156

Max Act: 1.2910. Min Act: -0.0000

Data Index: 1470226 (Python Code)

Max Activating Token Index: 163

Text #2

Max Range: 1.3156. Min Range: -1.3156

Max Act: 1.2880. Min Act: -0.0000

Data Index: 1427616 (Python Code)

Max Activating Token Index: 653

Text #3

Max Range: 1.3156. Min Range: -1.3156

Max Act: 1.0053. Min Act: -0.0000

Data Index: 1548336 (Python Code)

Max Activating Token Index: 166

Text #4

Max Range: 1.3156. Min Range: -1.3156

Max Act: 1.2120. Min Act: -0.0000

Data Index: 1591806 (Python Code)

Max Activating Token Index: 318

Text #5

Max Range: 1.3156. Min Range: -1.3156

Max Act: 1.3156. Min Act: -0.0000

Data Index: 1603999 (Python Code)

Max Activating Token Index: 221

Text #6

Max Range: 1.3156. Min Range: -1.3156

Max Act: 1.2053. Min Act: -0.0000

Data Index: 1485802 (Python Code)

Max Activating Token Index: 941

Text #7

Max Range: 1.3156. Min Range: -1.3156

Max Act: 1.0627. Min Act: -0.0000

Data Index: 1570712 (Python Code)

Max Activating Token Index: 154

Text #8

Max Range: 1.3156. Min Range: -1.3156

Max Act: 1.0159. Min Act: -0.0000

Data Index: 1428335 (Python Code)

Max Activating Token Index: 150

Text #9

Max Range: 1.3156. Min Range: -1.3156

Max Act: 0.9745. Min Act: -0.0000

Data Index: 1479931 (Python Code)

Max Activating Token Index: 153

Text #10

Max Range: 1.3156. Min Range: -1.3156

Max Act: 0.9503. Min Act: -0.0000

Data Index: 1582684 (Python Code)

Max Activating Token Index: 320

Text #11

Max Range: 1.3156. Min Range: -1.3156

Max Act: 1.0002. Min Act: -0.0000

Data Index: 1616155 (Python Code)

Max Activating Token Index: 281

Text #12

Max Range: 1.3156. Min Range: -1.3156

Max Act: 1.0210. Min Act: -0.0000

Data Index: 1479339 (Python Code)

Max Activating Token Index: 240

Text #13

Max Range: 1.3156. Min Range: -1.3156

Max Act: 0.9904. Min Act: -0.0000

Data Index: 1440200 (Python Code)

Max Activating Token Index: 159

Text #14

Max Range: 1.3156. Min Range: -1.3156

Max Act: 0.9706. Min Act: -0.0000

Data Index: 1622489 (Python Code)

Max Activating Token Index: 267

Text #15

Max Range: 1.3156. Min Range: -1.3156

Max Act: 1.0641. Min Act: -0.0000

Data Index: 1389852 (Python Code)

Max Activating Token Index: 195

Text #16

Max Range: 1.3156. Min Range: -1.3156

Max Act: 0.9290. Min Act: -0.0000

Data Index: 1498427 (Python Code)

Max Activating Token Index: 94

Text #17

Max Range: 1.3156. Min Range: -1.3156

Max Act: 1.0294. Min Act: -0.0000

Data Index: 1513923 (Python Code)

Max Activating Token Index: 289

Text #18

Max Range: 1.3156. Min Range: -1.3156

Max Act: 0.9896. Min Act: -0.0000

Data Index: 1434438 (Python Code)

Max Activating Token Index: 93

Text #19

Max Range: 1.3156. Min Range: -1.3156

Max Act: 0.9363. Min Act: -0.0000

Data Index: 1569820 (Python Code)

Max Activating Token Index: 403