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

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

Neuron 70 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: 0.0758. Min Range: -0.0758

Max Act: 0.0758. Min Act: -0.0002

Data Index: 199644 (C4 (Web Text))

Max Activating Token Index: 280

Text #1

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0689. Min Act: -0.0002

Data Index: 329001 (C4 (Web Text))

Max Activating Token Index: 236

Text #2

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0673. Min Act: -0.0002

Data Index: 805292 (C4 (Web Text))

Max Activating Token Index: 297

Text #3

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0713. Min Act: -0.0002

Data Index: 452581 (C4 (Web Text))

Max Activating Token Index: 781

Text #4

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0675. Min Act: -0.0002

Data Index: 589712 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0673. Min Act: -0.0001

Data Index: 1097118 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0670. Min Act: -0.0002

Data Index: 345416 (C4 (Web Text))

Max Activating Token Index: 54

Text #7

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0679. Min Act: -0.0002

Data Index: 852479 (C4 (Web Text))

Max Activating Token Index: 459

Text #8

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0680. Min Act: -0.0002

Data Index: 225115 (C4 (Web Text))

Max Activating Token Index: 366

Text #9

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0670. Min Act: -0.0002

Data Index: 1117183 (C4 (Web Text))

Max Activating Token Index: 652

Text #10

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0639. Min Act: -0.0002

Data Index: 142172 (C4 (Web Text))

Max Activating Token Index: 345

Text #11

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0655. Min Act: -0.0002

Data Index: 523070 (C4 (Web Text))

Max Activating Token Index: 628

Text #12

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0665. Min Act: -0.0002

Data Index: 109367 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0643. Min Act: -0.0002

Data Index: 10490 (C4 (Web Text))

Max Activating Token Index: 124

Text #14

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0653. Min Act: -0.0002

Data Index: 321831 (C4 (Web Text))

Max Activating Token Index: 225

Text #15

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0619. Min Act: -0.0002

Data Index: 206506 (C4 (Web Text))

Max Activating Token Index: 1007

Text #16

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0628. Min Act: -0.0002

Data Index: 180010 (C4 (Web Text))

Max Activating Token Index: 778

Text #17

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0624. Min Act: -0.0002

Data Index: 443772 (C4 (Web Text))

Max Activating Token Index: 404

Text #18

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0646. Min Act: -0.0002

Data Index: 1124436 (C4 (Web Text))

Max Activating Token Index: 831

Text #19

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0647. Min Act: -0.0002

Data Index: 770942 (C4 (Web Text))

Max Activating Token Index: 152