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

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

Neuron 4497 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5130. Min Range: -1.5130

Max Act: 1.5130. Min Act: -0.0001

Data Index: 395078 (C4 (Web Text))

Max Activating Token Index: 924

Text #1

Max Range: 1.5130. Min Range: -1.5130

Max Act: 1.4473. Min Act: -0.0001

Data Index: 1168583 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 1.5130. Min Range: -1.5130

Max Act: 1.2331. Min Act: -0.0001

Data Index: 1090626 (C4 (Web Text))

Max Activating Token Index: 400

Text #3

Max Range: 1.5130. Min Range: -1.5130

Max Act: 1.2999. Min Act: -0.0001

Data Index: 891921 (C4 (Web Text))

Max Activating Token Index: 688

Text #4

Max Range: 1.5130. Min Range: -1.5130

Max Act: 1.1832. Min Act: -0.0001

Data Index: 1036657 (C4 (Web Text))

Max Activating Token Index: 874

Text #5

Max Range: 1.5130. Min Range: -1.5130

Max Act: 1.0159. Min Act: -0.0001

Data Index: 977584 (C4 (Web Text))

Max Activating Token Index: 319

Text #6

Max Range: 1.5130. Min Range: -1.5130

Max Act: 1.0900. Min Act: -0.0001

Data Index: 103334 (C4 (Web Text))

Max Activating Token Index: 130

Text #7

Max Range: 1.5130. Min Range: -1.5130

Max Act: 1.0304. Min Act: -0.0001

Data Index: 1214281 (C4 (Web Text))

Max Activating Token Index: 810

Text #8

Max Range: 1.5130. Min Range: -1.5130

Max Act: 1.0674. Min Act: -0.0001

Data Index: 765259 (C4 (Web Text))

Max Activating Token Index: 869

Text #9

Max Range: 1.5130. Min Range: -1.5130

Max Act: 1.0551. Min Act: -0.0001

Data Index: 774537 (C4 (Web Text))

Max Activating Token Index: 963

Text #10

Max Range: 1.5130. Min Range: -1.5130

Max Act: 1.1070. Min Act: -0.0001

Data Index: 590495 (C4 (Web Text))

Max Activating Token Index: 849

Text #11

Max Range: 1.5130. Min Range: -1.5130

Max Act: 1.0993. Min Act: -0.0001

Data Index: 1111658 (C4 (Web Text))

Max Activating Token Index: 491

Text #12

Max Range: 1.5130. Min Range: -1.5130

Max Act: 0.9648. Min Act: -0.0001

Data Index: 665061 (C4 (Web Text))

Max Activating Token Index: 819

Text #13

Max Range: 1.5130. Min Range: -1.5130

Max Act: 0.9873. Min Act: -0.0001

Data Index: 1316639 (C4 (Web Text))

Max Activating Token Index: 265

Text #14

Max Range: 1.5130. Min Range: -1.5130

Max Act: 0.9894. Min Act: -0.0001

Data Index: 739752 (C4 (Web Text))

Max Activating Token Index: 951

Text #15

Max Range: 1.5130. Min Range: -1.5130

Max Act: 0.9524. Min Act: -0.0001

Data Index: 686273 (C4 (Web Text))

Max Activating Token Index: 1004

Text #16

Max Range: 1.5130. Min Range: -1.5130

Max Act: 0.8759. Min Act: -0.0001

Data Index: 1227436 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 1.5130. Min Range: -1.5130

Max Act: 0.9298. Min Act: -0.0001

Data Index: 1263538 (C4 (Web Text))

Max Activating Token Index: 221

Text #18

Max Range: 1.5130. Min Range: -1.5130

Max Act: 0.8957. Min Act: -0.0001

Data Index: 710088 (C4 (Web Text))

Max Activating Token Index: 922

Text #19

Max Range: 1.5130. Min Range: -1.5130

Max Act: 0.8419. Min Act: -0.0001

Data Index: 352130 (C4 (Web Text))

Max Activating Token Index: 719