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

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

Neuron 4708 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.1172. Min Act: -0.0002

Data Index: 1014517 (C4 (Web Text))

Max Activating Token Index: 128

Text #1

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.1151. Min Act: -0.0003

Data Index: 491015 (C4 (Web Text))

Max Activating Token Index: 867

Text #2

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.1037. Min Act: -0.0002

Data Index: 1309180 (C4 (Web Text))

Max Activating Token Index: 360

Text #3

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0970. Min Act: -0.0002

Data Index: 781288 (C4 (Web Text))

Max Activating Token Index: 432

Text #4

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0854. Min Act: -0.0002

Data Index: 140534 (C4 (Web Text))

Max Activating Token Index: 396

Text #5

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0912. Min Act: -0.0003

Data Index: 406441 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0836. Min Act: -0.0002

Data Index: 477691 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0806. Min Act: -0.0002

Data Index: 604413 (C4 (Web Text))

Max Activating Token Index: 957

Text #8

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0819. Min Act: -0.0002

Data Index: 30400 (C4 (Web Text))

Max Activating Token Index: 141

Text #9

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0800. Min Act: -0.0002

Data Index: 282330 (C4 (Web Text))

Max Activating Token Index: 1014

Text #10

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0826. Min Act: -0.0002

Data Index: 991237 (C4 (Web Text))

Max Activating Token Index: 290

Text #11

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0828. Min Act: -0.0003

Data Index: 1236952 (C4 (Web Text))

Max Activating Token Index: 266

Text #12

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0748. Min Act: -0.0002

Data Index: 8025 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0767. Min Act: -0.0003

Data Index: 1141343 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0739. Min Act: -0.0002

Data Index: 608996 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0747. Min Act: -0.0002

Data Index: 132197 (C4 (Web Text))

Max Activating Token Index: 174

Text #16

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0755. Min Act: -0.0002

Data Index: 340873 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0749. Min Act: -0.0002

Data Index: 60896 (C4 (Web Text))

Max Activating Token Index: 466

Text #18

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0718. Min Act: -0.0002

Data Index: 851895 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0739. Min Act: -0.0003

Data Index: 829347 (C4 (Web Text))

Max Activating Token Index: 818