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

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

Neuron 862 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0658. Min Act: -0.0005

Data Index: 1305910 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0658. Min Act: -0.0004

Data Index: 324335 (C4 (Web Text))

Max Activating Token Index: 443

Text #2

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0690. Min Act: -0.0005

Data Index: 766872 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0676. Min Act: -0.0005

Data Index: 398824 (C4 (Web Text))

Max Activating Token Index: 422

Text #4

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0634. Min Act: -0.0005

Data Index: 13481 (C4 (Web Text))

Max Activating Token Index: 361

Text #5

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0662. Min Act: -0.0005

Data Index: 555229 (C4 (Web Text))

Max Activating Token Index: 915

Text #6

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0654. Min Act: -0.0005

Data Index: 631804 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0679. Min Act: -0.0005

Data Index: 446568 (C4 (Web Text))

Max Activating Token Index: 219

Text #8

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0620. Min Act: -0.0005

Data Index: 1052427 (C4 (Web Text))

Max Activating Token Index: 507

Text #9

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0643. Min Act: -0.0005

Data Index: 177380 (C4 (Web Text))

Max Activating Token Index: 606

Text #10

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0612. Min Act: -0.0005

Data Index: 598382 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0636. Min Act: -0.0005

Data Index: 1321445 (C4 (Web Text))

Max Activating Token Index: 553

Text #12

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0624. Min Act: -0.0005

Data Index: 1292441 (C4 (Web Text))

Max Activating Token Index: 264

Text #13

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0607. Min Act: -0.0005

Data Index: 421939 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0646. Min Act: -0.0005

Data Index: 1223727 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0633. Min Act: -0.0005

Data Index: 1158956 (C4 (Web Text))

Max Activating Token Index: 202

Text #16

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0632. Min Act: -0.0005

Data Index: 1142479 (C4 (Web Text))

Max Activating Token Index: 837

Text #17

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0604. Min Act: -0.0005

Data Index: 833889 (C4 (Web Text))

Max Activating Token Index: 213

Text #18

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0600. Min Act: -0.0005

Data Index: 1215860 (C4 (Web Text))

Max Activating Token Index: 989

Text #19

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0599. Min Act: -0.0005

Data Index: 468533 (C4 (Web Text))

Max Activating Token Index: 889