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

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

Neuron 4819 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.1058. Min Act: -0.0002

Data Index: 245629 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0797. Min Act: -0.0002

Data Index: 517824 (C4 (Web Text))

Max Activating Token Index: 219

Text #2

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0836. Min Act: -0.0002

Data Index: 112804 (C4 (Web Text))

Max Activating Token Index: 231

Text #3

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0773. Min Act: -0.0002

Data Index: 752403 (C4 (Web Text))

Max Activating Token Index: 309

Text #4

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0764. Min Act: -0.0002

Data Index: 218364 (C4 (Web Text))

Max Activating Token Index: 524

Text #5

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0780. Min Act: -0.0002

Data Index: 1148960 (C4 (Web Text))

Max Activating Token Index: 392

Text #6

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0760. Min Act: -0.0002

Data Index: 656565 (C4 (Web Text))

Max Activating Token Index: 287

Text #7

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0781. Min Act: -0.0002

Data Index: 566440 (C4 (Web Text))

Max Activating Token Index: 595

Text #8

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0753. Min Act: -0.0002

Data Index: 679937 (C4 (Web Text))

Max Activating Token Index: 488

Text #9

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0769. Min Act: -0.0002

Data Index: 19987 (C4 (Web Text))

Max Activating Token Index: 331

Text #10

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0731. Min Act: -0.0002

Data Index: 1107106 (C4 (Web Text))

Max Activating Token Index: 359

Text #11

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0724. Min Act: -0.0002

Data Index: 419963 (C4 (Web Text))

Max Activating Token Index: 337

Text #12

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0726. Min Act: -0.0002

Data Index: 255825 (C4 (Web Text))

Max Activating Token Index: 512

Text #13

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0688. Min Act: -0.0002

Data Index: 356657 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0682. Min Act: -0.0002

Data Index: 972323 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0686. Min Act: -0.0002

Data Index: 683938 (C4 (Web Text))

Max Activating Token Index: 583

Text #16

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0703. Min Act: -0.0002

Data Index: 844660 (C4 (Web Text))

Max Activating Token Index: 753

Text #17

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0751. Min Act: -0.0002

Data Index: 618036 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0679. Min Act: -0.0002

Data Index: 458816 (C4 (Web Text))

Max Activating Token Index: 288

Text #19

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0651. Min Act: -0.0002

Data Index: 58743 (C4 (Web Text))

Max Activating Token Index: 280