Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 88 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.0963. Min Range: -2.0963

Max Act: 2.0755. Min Act: -0.0000

Data Index: 93730 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 2.0963. Min Range: -2.0963

Max Act: 2.0753. Min Act: -0.0000

Data Index: 866648 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 2.0963. Min Range: -2.0963

Max Act: 2.0226. Min Act: -0.0000

Data Index: 359249 (C4 (Web Text))

Max Activating Token Index: 918

Text #3

Max Range: 2.0963. Min Range: -2.0963

Max Act: 2.0887. Min Act: -0.0000

Data Index: 931700 (C4 (Web Text))

Max Activating Token Index: 681

Text #4

Max Range: 2.0963. Min Range: -2.0963

Max Act: 2.0963. Min Act: -0.0000

Data Index: 39350 (C4 (Web Text))

Max Activating Token Index: 372

Text #5

Max Range: 2.0963. Min Range: -2.0963

Max Act: 1.8678. Min Act: -0.0000

Data Index: 867587 (C4 (Web Text))

Max Activating Token Index: 880

Text #6

Max Range: 2.0963. Min Range: -2.0963

Max Act: 2.0198. Min Act: -0.0000

Data Index: 455784 (C4 (Web Text))

Max Activating Token Index: 1015

Text #7

Max Range: 2.0963. Min Range: -2.0963

Max Act: 1.9495. Min Act: -0.0000

Data Index: 1011887 (C4 (Web Text))

Max Activating Token Index: 140

Text #8

Max Range: 2.0963. Min Range: -2.0963

Max Act: 1.8376. Min Act: -0.0000

Data Index: 763742 (C4 (Web Text))

Max Activating Token Index: 922

Text #9

Max Range: 2.0963. Min Range: -2.0963

Max Act: 1.7969. Min Act: -0.0000

Data Index: 1073227 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 2.0963. Min Range: -2.0963

Max Act: 1.7783. Min Act: -0.0000

Data Index: 1049400 (C4 (Web Text))

Max Activating Token Index: 693

Text #11

Max Range: 2.0963. Min Range: -2.0963

Max Act: 1.6689. Min Act: -0.0000

Data Index: 457760 (C4 (Web Text))

Max Activating Token Index: 500

Text #12

Max Range: 2.0963. Min Range: -2.0963

Max Act: 1.7478. Min Act: -0.0000

Data Index: 767556 (C4 (Web Text))

Max Activating Token Index: 867

Text #13

Max Range: 2.0963. Min Range: -2.0963

Max Act: 1.6401. Min Act: -0.0000

Data Index: 403998 (C4 (Web Text))

Max Activating Token Index: 491

Text #14

Max Range: 2.0963. Min Range: -2.0963

Max Act: 1.4736. Min Act: -0.0000

Data Index: 1380239 (Python Code)

Max Activating Token Index: 209

Text #15

Max Range: 2.0963. Min Range: -2.0963

Max Act: 1.6825. Min Act: -0.0000

Data Index: 1058518 (C4 (Web Text))

Max Activating Token Index: 500

Text #16

Max Range: 2.0963. Min Range: -2.0963

Max Act: 1.6800. Min Act: -0.0000

Data Index: 1178958 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 2.0963. Min Range: -2.0963

Max Act: 1.6609. Min Act: -0.0000

Data Index: 727004 (C4 (Web Text))

Max Activating Token Index: 572

Text #18

Max Range: 2.0963. Min Range: -2.0963

Max Act: 1.6602. Min Act: -0.0000

Data Index: 376610 (C4 (Web Text))

Max Activating Token Index: 170

Text #19

Max Range: 2.0963. Min Range: -2.0963

Max Act: 1.6455. Min Act: -0.0000

Data Index: 1014886 (C4 (Web Text))

Max Activating Token Index: 665