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

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

Neuron 2502 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: 1.9173. Min Range: -1.9173

Max Act: 1.9173. Min Act: -0.0002

Data Index: 233547 (C4 (Web Text))

Max Activating Token Index: 501

Text #1

Max Range: 1.9173. Min Range: -1.9173

Max Act: 1.4826. Min Act: -0.0002

Data Index: 723094 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 1.9173. Min Range: -1.9173

Max Act: 1.4161. Min Act: -0.0003

Data Index: 75185 (C4 (Web Text))

Max Activating Token Index: 73

Text #3

Max Range: 1.9173. Min Range: -1.9173

Max Act: 1.3208. Min Act: -0.0003

Data Index: 468533 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 1.9173. Min Range: -1.9173

Max Act: 1.3457. Min Act: -0.0002

Data Index: 42905 (C4 (Web Text))

Max Activating Token Index: 266

Text #5

Max Range: 1.9173. Min Range: -1.9173

Max Act: 1.3095. Min Act: -0.0002

Data Index: 749031 (C4 (Web Text))

Max Activating Token Index: 627

Text #6

Max Range: 1.9173. Min Range: -1.9173

Max Act: 1.2066. Min Act: -0.0002

Data Index: 172336 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 1.9173. Min Range: -1.9173

Max Act: 1.2021. Min Act: -0.0003

Data Index: 517845 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 1.9173. Min Range: -1.9173

Max Act: 1.2343. Min Act: -0.0003

Data Index: 1026073 (C4 (Web Text))

Max Activating Token Index: 185

Text #9

Max Range: 1.9173. Min Range: -1.9173

Max Act: 1.2144. Min Act: -0.0003

Data Index: 969176 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 1.9173. Min Range: -1.9173

Max Act: 1.2077. Min Act: -0.0002

Data Index: 1332565 (C4 (Web Text))

Max Activating Token Index: 637

Text #11

Max Range: 1.9173. Min Range: -1.9173

Max Act: 1.2097. Min Act: -0.0002

Data Index: 543472 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 1.9173. Min Range: -1.9173

Max Act: 1.1937. Min Act: -0.0002

Data Index: 753725 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 1.9173. Min Range: -1.9173

Max Act: 1.1836. Min Act: -0.0002

Data Index: 26931 (C4 (Web Text))

Max Activating Token Index: 238

Text #14

Max Range: 1.9173. Min Range: -1.9173

Max Act: 1.1819. Min Act: -0.0002

Data Index: 1292614 (C4 (Web Text))

Max Activating Token Index: 85

Text #15

Max Range: 1.9173. Min Range: -1.9173

Max Act: 1.1631. Min Act: -0.0002

Data Index: 371828 (C4 (Web Text))

Max Activating Token Index: 769

Text #16

Max Range: 1.9173. Min Range: -1.9173

Max Act: 1.1637. Min Act: -0.0002

Data Index: 337423 (C4 (Web Text))

Max Activating Token Index: 244

Text #17

Max Range: 1.9173. Min Range: -1.9173

Max Act: 1.1584. Min Act: -0.0002

Data Index: 836618 (C4 (Web Text))

Max Activating Token Index: 500

Text #18

Max Range: 1.9173. Min Range: -1.9173

Max Act: 1.1254. Min Act: -0.0002

Data Index: 967053 (C4 (Web Text))

Max Activating Token Index: 339

Text #19

Max Range: 1.9173. Min Range: -1.9173

Max Act: 1.1178. Min Act: -0.0002

Data Index: 1266196 (C4 (Web Text))

Max Activating Token Index: 49