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

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

Neuron 5223 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1368. Min Act: -0.0000

Data Index: 1545324 (Python Code)

Max Activating Token Index: 141

Text #1

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1246. Min Act: -0.0000

Data Index: 1592993 (Python Code)

Max Activating Token Index: 88

Text #2

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1380. Min Act: -0.0000

Data Index: 1644392 (Python Code)

Max Activating Token Index: 377

Text #3

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1248. Min Act: -0.0000

Data Index: 1411246 (Python Code)

Max Activating Token Index: 437

Text #4

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1368. Min Act: -0.0000

Data Index: 761160 (C4 (Web Text))

Max Activating Token Index: 213

Text #5

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1068. Min Act: -0.0000

Data Index: 1593737 (Python Code)

Max Activating Token Index: 118

Text #6

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1193. Min Act: -0.0000

Data Index: 1332919 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1074. Min Act: -0.0000

Data Index: 633457 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0977. Min Act: -0.0000

Data Index: 1193481 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0948. Min Act: -0.0000

Data Index: 952776 (C4 (Web Text))

Max Activating Token Index: 111

Text #10

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0930. Min Act: -0.0000

Data Index: 1535518 (Python Code)

Max Activating Token Index: 613

Text #11

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0993. Min Act: -0.0000

Data Index: 1433321 (Python Code)

Max Activating Token Index: 138

Text #12

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0922. Min Act: -0.0000

Data Index: 47595 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0892. Min Act: -0.0000

Data Index: 1543940 (Python Code)

Max Activating Token Index: 173

Text #14

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0845. Min Act: -0.0000

Data Index: 1332618 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0812. Min Act: -0.0000

Data Index: 1492736 (Python Code)

Max Activating Token Index: 259

Text #16

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0801. Min Act: -0.0000

Data Index: 534871 (C4 (Web Text))

Max Activating Token Index: 406

Text #17

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0873. Min Act: -0.0000

Data Index: 1372344 (Python Code)

Max Activating Token Index: 70

Text #18

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0809. Min Act: -0.0000

Data Index: 878015 (C4 (Web Text))

Max Activating Token Index: 201

Text #19

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0831. Min Act: -0.0000

Data Index: 296897 (C4 (Web Text))

Max Activating Token Index: 143