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

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

Neuron 2417 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 16.8952. Min Range: -16.8952

Max Act: 16.8952. Min Act: -0.0000

Data Index: 110337 (C4 (Web Text))

Max Activating Token Index: 499

Text #1

Max Range: 16.8952. Min Range: -16.8952

Max Act: 16.6063. Min Act: -0.0001

Data Index: 555771 (C4 (Web Text))

Max Activating Token Index: 566

Text #2

Max Range: 16.8952. Min Range: -16.8952

Max Act: 15.9755. Min Act: -0.0000

Data Index: 1204397 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 16.8952. Min Range: -16.8952

Max Act: 15.8139. Min Act: -0.0000

Data Index: 194810 (C4 (Web Text))

Max Activating Token Index: 203

Text #4

Max Range: 16.8952. Min Range: -16.8952

Max Act: 15.7718. Min Act: -0.0001

Data Index: 339418 (C4 (Web Text))

Max Activating Token Index: 249

Text #5

Max Range: 16.8952. Min Range: -16.8952

Max Act: 15.7699. Min Act: -0.0001

Data Index: 76287 (C4 (Web Text))

Max Activating Token Index: 217

Text #6

Max Range: 16.8952. Min Range: -16.8952

Max Act: 15.7294. Min Act: -0.0000

Data Index: 488361 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 16.8952. Min Range: -16.8952

Max Act: 15.4718. Min Act: -0.0000

Data Index: 145827 (C4 (Web Text))

Max Activating Token Index: 242

Text #8

Max Range: 16.8952. Min Range: -16.8952

Max Act: 15.6884. Min Act: -0.0000

Data Index: 3395 (C4 (Web Text))

Max Activating Token Index: 199

Text #9

Max Range: 16.8952. Min Range: -16.8952

Max Act: 15.6536. Min Act: -0.0000

Data Index: 800739 (C4 (Web Text))

Max Activating Token Index: 277

Text #10

Max Range: 16.8952. Min Range: -16.8952

Max Act: 15.6523. Min Act: -0.0000

Data Index: 1167687 (C4 (Web Text))

Max Activating Token Index: 251

Text #11

Max Range: 16.8952. Min Range: -16.8952

Max Act: 15.6430. Min Act: -0.0000

Data Index: 803674 (C4 (Web Text))

Max Activating Token Index: 8

Text #12

Max Range: 16.8952. Min Range: -16.8952

Max Act: 15.6007. Min Act: -0.0000

Data Index: 1301624 (C4 (Web Text))

Max Activating Token Index: 211

Text #13

Max Range: 16.8952. Min Range: -16.8952

Max Act: 15.6435. Min Act: -0.0000

Data Index: 1074275 (C4 (Web Text))

Max Activating Token Index: 261

Text #14

Max Range: 16.8952. Min Range: -16.8952

Max Act: 15.5617. Min Act: -0.0000

Data Index: 1052114 (C4 (Web Text))

Max Activating Token Index: 261

Text #15

Max Range: 16.8952. Min Range: -16.8952

Max Act: 15.6101. Min Act: -0.0001

Data Index: 1223684 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 16.8952. Min Range: -16.8952

Max Act: 15.6071. Min Act: -0.0000

Data Index: 1113885 (C4 (Web Text))

Max Activating Token Index: 7

Text #17

Max Range: 16.8952. Min Range: -16.8952

Max Act: 15.6051. Min Act: -0.0000

Data Index: 286814 (C4 (Web Text))

Max Activating Token Index: 88

Text #18

Max Range: 16.8952. Min Range: -16.8952

Max Act: 15.6037. Min Act: -0.0000

Data Index: 546010 (C4 (Web Text))

Max Activating Token Index: 181

Text #19

Max Range: 16.8952. Min Range: -16.8952

Max Act: 15.6026. Min Act: -0.0000

Data Index: 602336 (C4 (Web Text))

Max Activating Token Index: 243