Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 771 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0854. Min Act: -0.0002

Data Index: 1346815 (C4 (Web Text))

Max Activating Token Index: 294

Text #1

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0832. Min Act: -0.0002

Data Index: 494480 (C4 (Web Text))

Max Activating Token Index: 328

Text #2

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0767. Min Act: -0.0002

Data Index: 695030 (C4 (Web Text))

Max Activating Token Index: 206

Text #3

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0760. Min Act: -0.0002

Data Index: 942494 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0729. Min Act: -0.0002

Data Index: 647294 (C4 (Web Text))

Max Activating Token Index: 235

Text #5

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0735. Min Act: -0.0002

Data Index: 263737 (C4 (Web Text))

Max Activating Token Index: 226

Text #6

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0715. Min Act: -0.0002

Data Index: 814331 (C4 (Web Text))

Max Activating Token Index: 134

Text #7

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0709. Min Act: -0.0002

Data Index: 208699 (C4 (Web Text))

Max Activating Token Index: 191

Text #8

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0696. Min Act: -0.0002

Data Index: 843544 (C4 (Web Text))

Max Activating Token Index: 498

Text #9

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0701. Min Act: -0.0002

Data Index: 842049 (C4 (Web Text))

Max Activating Token Index: 378

Text #10

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0677. Min Act: -0.0002

Data Index: 334288 (C4 (Web Text))

Max Activating Token Index: 437

Text #11

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0695. Min Act: -0.0002

Data Index: 471822 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0673. Min Act: -0.0002

Data Index: 258773 (C4 (Web Text))

Max Activating Token Index: 963

Text #13

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0656. Min Act: -0.0002

Data Index: 770600 (C4 (Web Text))

Max Activating Token Index: 541

Text #14

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0660. Min Act: -0.0002

Data Index: 550747 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0658. Min Act: -0.0002

Data Index: 215324 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0647. Min Act: -0.0002

Data Index: 1119430 (C4 (Web Text))

Max Activating Token Index: 17

Text #17

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0615. Min Act: -0.0002

Data Index: 539622 (C4 (Web Text))

Max Activating Token Index: 289

Text #18

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0634. Min Act: -0.0002

Data Index: 487644 (C4 (Web Text))

Max Activating Token Index: 337

Text #19

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0642. Min Act: -0.0002

Data Index: 543359 (C4 (Web Text))

Max Activating Token Index: 356