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

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

Neuron 4127 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.8354. Min Act: -0.0001

Data Index: 207224 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.5252. Min Act: -0.0001

Data Index: 311106 (C4 (Web Text))

Max Activating Token Index: 304

Text #2

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.2079. Min Act: -0.0001

Data Index: 5189 (C4 (Web Text))

Max Activating Token Index: 792

Text #3

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.2692. Min Act: -0.0001

Data Index: 282552 (C4 (Web Text))

Max Activating Token Index: 432

Text #4

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.1682. Min Act: -0.0001

Data Index: 199508 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.1583. Min Act: -0.0001

Data Index: 1043827 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.1634. Min Act: -0.0001

Data Index: 1107257 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.0261. Min Act: -0.0001

Data Index: 389376 (C4 (Web Text))

Max Activating Token Index: 261

Text #8

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.0599. Min Act: -0.0001

Data Index: 528348 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.1027. Min Act: -0.0001

Data Index: 535672 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.0664. Min Act: -0.0001

Data Index: 103727 (C4 (Web Text))

Max Activating Token Index: 731

Text #11

Max Range: 1.8354. Min Range: -1.8354

Max Act: 0.9930. Min Act: -0.0001

Data Index: 657262 (C4 (Web Text))

Max Activating Token Index: 222

Text #12

Max Range: 1.8354. Min Range: -1.8354

Max Act: 0.9190. Min Act: -0.0001

Data Index: 884075 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 1.8354. Min Range: -1.8354

Max Act: 0.9018. Min Act: -0.0001

Data Index: 1107212 (C4 (Web Text))

Max Activating Token Index: 163

Text #14

Max Range: 1.8354. Min Range: -1.8354

Max Act: 0.8934. Min Act: -0.0001

Data Index: 158334 (C4 (Web Text))

Max Activating Token Index: 360

Text #15

Max Range: 1.8354. Min Range: -1.8354

Max Act: 0.9605. Min Act: -0.0001

Data Index: 1022414 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 1.8354. Min Range: -1.8354

Max Act: 0.9354. Min Act: -0.0001

Data Index: 273265 (C4 (Web Text))

Max Activating Token Index: 295

Text #17

Max Range: 1.8354. Min Range: -1.8354

Max Act: 0.8880. Min Act: -0.0001

Data Index: 1298974 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 1.8354. Min Range: -1.8354

Max Act: 0.8690. Min Act: -0.0001

Data Index: 1065330 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 1.8354. Min Range: -1.8354

Max Act: 0.8598. Min Act: -0.0001

Data Index: 29189 (C4 (Web Text))

Max Activating Token Index: 129