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

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

Neuron 3961 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1093. Min Range: -2.1093

Max Act: 2.0316. Min Act: -0.0000

Data Index: 490913 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 2.1093. Min Range: -2.1093

Max Act: 2.1093. Min Act: -0.0000

Data Index: 239833 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 2.1093. Min Range: -2.1093

Max Act: 1.9970. Min Act: -0.0000

Data Index: 56439 (C4 (Web Text))

Max Activating Token Index: 171

Text #3

Max Range: 2.1093. Min Range: -2.1093

Max Act: 1.9450. Min Act: -0.0000

Data Index: 1141940 (C4 (Web Text))

Max Activating Token Index: 422

Text #4

Max Range: 2.1093. Min Range: -2.1093

Max Act: 1.8880. Min Act: -0.0000

Data Index: 896287 (C4 (Web Text))

Max Activating Token Index: 897

Text #5

Max Range: 2.1093. Min Range: -2.1093

Max Act: 1.9824. Min Act: -0.0000

Data Index: 734722 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 2.1093. Min Range: -2.1093

Max Act: 1.8012. Min Act: -0.0000

Data Index: 703984 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 2.1093. Min Range: -2.1093

Max Act: 1.7796. Min Act: -0.0000

Data Index: 1346724 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 2.1093. Min Range: -2.1093

Max Act: 1.7946. Min Act: -0.0000

Data Index: 164983 (C4 (Web Text))

Max Activating Token Index: 337

Text #9

Max Range: 2.1093. Min Range: -2.1093

Max Act: 1.6519. Min Act: -0.0000

Data Index: 83954 (C4 (Web Text))

Max Activating Token Index: 626

Text #10

Max Range: 2.1093. Min Range: -2.1093

Max Act: 1.8618. Min Act: -0.0000

Data Index: 908388 (C4 (Web Text))

Max Activating Token Index: 544

Text #11

Max Range: 2.1093. Min Range: -2.1093

Max Act: 1.4559. Min Act: -0.0000

Data Index: 1319139 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 2.1093. Min Range: -2.1093

Max Act: 1.5395. Min Act: -0.0000

Data Index: 724926 (C4 (Web Text))

Max Activating Token Index: 582

Text #13

Max Range: 2.1093. Min Range: -2.1093

Max Act: 1.7115. Min Act: -0.0000

Data Index: 1109473 (C4 (Web Text))

Max Activating Token Index: 708

Text #14

Max Range: 2.1093. Min Range: -2.1093

Max Act: 1.8360. Min Act: -0.0000

Data Index: 424186 (C4 (Web Text))

Max Activating Token Index: 530

Text #15

Max Range: 2.1093. Min Range: -2.1093

Max Act: 1.5809. Min Act: -0.0000

Data Index: 283678 (C4 (Web Text))

Max Activating Token Index: 752

Text #16

Max Range: 2.1093. Min Range: -2.1093

Max Act: 1.5109. Min Act: -0.0000

Data Index: 197728 (C4 (Web Text))

Max Activating Token Index: 282

Text #17

Max Range: 2.1093. Min Range: -2.1093

Max Act: 1.6548. Min Act: -0.0000

Data Index: 22153 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 2.1093. Min Range: -2.1093

Max Act: 1.5586. Min Act: -0.0000

Data Index: 73545 (C4 (Web Text))

Max Activating Token Index: 751

Text #19

Max Range: 2.1093. Min Range: -2.1093

Max Act: 1.4738. Min Act: -0.0000

Data Index: 387381 (C4 (Web Text))

Max Activating Token Index: 708