Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1785 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.1051. Min Range: -2.1051

Max Act: 1.9729. Min Act: -0.0001

Data Index: 1043839 (C4 (Web Text))

Max Activating Token Index: 218

Text #1

Max Range: 2.1051. Min Range: -2.1051

Max Act: 2.1051. Min Act: -0.0001

Data Index: 420651 (C4 (Web Text))

Max Activating Token Index: 82

Text #2

Max Range: 2.1051. Min Range: -2.1051

Max Act: 2.0062. Min Act: -0.0001

Data Index: 809318 (C4 (Web Text))

Max Activating Token Index: 631

Text #3

Max Range: 2.1051. Min Range: -2.1051

Max Act: 1.7882. Min Act: -0.0001

Data Index: 587107 (C4 (Web Text))

Max Activating Token Index: 511

Text #4

Max Range: 2.1051. Min Range: -2.1051

Max Act: 1.7658. Min Act: -0.0001

Data Index: 98757 (C4 (Web Text))

Max Activating Token Index: 226

Text #5

Max Range: 2.1051. Min Range: -2.1051

Max Act: 1.7874. Min Act: -0.0001

Data Index: 1303046 (C4 (Web Text))

Max Activating Token Index: 577

Text #6

Max Range: 2.1051. Min Range: -2.1051

Max Act: 1.6837. Min Act: -0.0001

Data Index: 518412 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 2.1051. Min Range: -2.1051

Max Act: 1.6250. Min Act: -0.0001

Data Index: 177357 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 2.1051. Min Range: -2.1051

Max Act: 1.5000. Min Act: -0.0001

Data Index: 559506 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 2.1051. Min Range: -2.1051

Max Act: 1.5867. Min Act: -0.0001

Data Index: 1207652 (C4 (Web Text))

Max Activating Token Index: 715

Text #10

Max Range: 2.1051. Min Range: -2.1051

Max Act: 1.6651. Min Act: -0.0001

Data Index: 966413 (C4 (Web Text))

Max Activating Token Index: 755

Text #11

Max Range: 2.1051. Min Range: -2.1051

Max Act: 1.5187. Min Act: -0.0001

Data Index: 197762 (C4 (Web Text))

Max Activating Token Index: 66

Text #12

Max Range: 2.1051. Min Range: -2.1051

Max Act: 1.5099. Min Act: -0.0001

Data Index: 29045 (C4 (Web Text))

Max Activating Token Index: 940

Text #13

Max Range: 2.1051. Min Range: -2.1051

Max Act: 1.4596. Min Act: -0.0001

Data Index: 812035 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 2.1051. Min Range: -2.1051

Max Act: 1.5345. Min Act: -0.0001

Data Index: 273237 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 2.1051. Min Range: -2.1051

Max Act: 1.4725. Min Act: -0.0001

Data Index: 943559 (C4 (Web Text))

Max Activating Token Index: 191

Text #16

Max Range: 2.1051. Min Range: -2.1051

Max Act: 1.5118. Min Act: -0.0001

Data Index: 1019201 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 2.1051. Min Range: -2.1051

Max Act: 1.4228. Min Act: -0.0001

Data Index: 1179827 (C4 (Web Text))

Max Activating Token Index: 277

Text #18

Max Range: 2.1051. Min Range: -2.1051

Max Act: 1.4684. Min Act: -0.0001

Data Index: 182297 (C4 (Web Text))

Max Activating Token Index: 255

Text #19

Max Range: 2.1051. Min Range: -2.1051

Max Act: 1.4259. Min Act: -0.0001

Data Index: 834138 (C4 (Web Text))

Max Activating Token Index: 898