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

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

Neuron 1030 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0559. Min Range: -2.0559

Max Act: 2.0049. Min Act: -0.0000

Data Index: 311722 (C4 (Web Text))

Max Activating Token Index: 636

Text #1

Max Range: 2.0559. Min Range: -2.0559

Max Act: 1.9640. Min Act: -0.0000

Data Index: 1007203 (C4 (Web Text))

Max Activating Token Index: 425

Text #2

Max Range: 2.0559. Min Range: -2.0559

Max Act: 2.0559. Min Act: -0.0000

Data Index: 492956 (C4 (Web Text))

Max Activating Token Index: 608

Text #3

Max Range: 2.0559. Min Range: -2.0559

Max Act: 1.9051. Min Act: -0.0001

Data Index: 1081095 (C4 (Web Text))

Max Activating Token Index: 678

Text #4

Max Range: 2.0559. Min Range: -2.0559

Max Act: 1.7003. Min Act: -0.0000

Data Index: 1306185 (C4 (Web Text))

Max Activating Token Index: 208

Text #5

Max Range: 2.0559. Min Range: -2.0559

Max Act: 1.8932. Min Act: -0.0000

Data Index: 1326611 (C4 (Web Text))

Max Activating Token Index: 396

Text #6

Max Range: 2.0559. Min Range: -2.0559

Max Act: 1.7702. Min Act: -0.0000

Data Index: 773778 (C4 (Web Text))

Max Activating Token Index: 62

Text #7

Max Range: 2.0559. Min Range: -2.0559

Max Act: 1.9296. Min Act: -0.0000

Data Index: 286304 (C4 (Web Text))

Max Activating Token Index: 519

Text #8

Max Range: 2.0559. Min Range: -2.0559

Max Act: 1.6764. Min Act: -0.0000

Data Index: 831153 (C4 (Web Text))

Max Activating Token Index: 591

Text #9

Max Range: 2.0559. Min Range: -2.0559

Max Act: 1.8038. Min Act: -0.0001

Data Index: 628787 (C4 (Web Text))

Max Activating Token Index: 244

Text #10

Max Range: 2.0559. Min Range: -2.0559

Max Act: 1.6239. Min Act: -0.0000

Data Index: 774286 (C4 (Web Text))

Max Activating Token Index: 123

Text #11

Max Range: 2.0559. Min Range: -2.0559

Max Act: 1.6860. Min Act: -0.0000

Data Index: 783422 (C4 (Web Text))

Max Activating Token Index: 518

Text #12

Max Range: 2.0559. Min Range: -2.0559

Max Act: 1.5737. Min Act: -0.0000

Data Index: 667593 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 2.0559. Min Range: -2.0559

Max Act: 1.7764. Min Act: -0.0000

Data Index: 780546 (C4 (Web Text))

Max Activating Token Index: 593

Text #14

Max Range: 2.0559. Min Range: -2.0559

Max Act: 1.4562. Min Act: -0.0000

Data Index: 206442 (C4 (Web Text))

Max Activating Token Index: 987

Text #15

Max Range: 2.0559. Min Range: -2.0559

Max Act: 1.6773. Min Act: -0.0000

Data Index: 366360 (C4 (Web Text))

Max Activating Token Index: 881

Text #16

Max Range: 2.0559. Min Range: -2.0559

Max Act: 1.4923. Min Act: -0.0000

Data Index: 1134815 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 2.0559. Min Range: -2.0559

Max Act: 1.9231. Min Act: -0.0000

Data Index: 295076 (C4 (Web Text))

Max Activating Token Index: 632

Text #18

Max Range: 2.0559. Min Range: -2.0559

Max Act: 1.7550. Min Act: -0.0000

Data Index: 499309 (C4 (Web Text))

Max Activating Token Index: 663

Text #19

Max Range: 2.0559. Min Range: -2.0559

Max Act: 1.6553. Min Act: -0.0000

Data Index: 554570 (C4 (Web Text))

Max Activating Token Index: 587