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

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

Neuron 731 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4495. Min Range: -3.4495

Max Act: 3.4495. Min Act: -0.0000

Data Index: 824421 (C4 (Web Text))

Max Activating Token Index: 948

Text #1

Max Range: 3.4495. Min Range: -3.4495

Max Act: 3.0419. Min Act: -0.0000

Data Index: 582211 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 3.4495. Min Range: -3.4495

Max Act: 2.7006. Min Act: -0.0000

Data Index: 527604 (C4 (Web Text))

Max Activating Token Index: 562

Text #3

Max Range: 3.4495. Min Range: -3.4495

Max Act: 2.5718. Min Act: -0.0000

Data Index: 555648 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 3.4495. Min Range: -3.4495

Max Act: 2.4379. Min Act: -0.0000

Data Index: 646306 (C4 (Web Text))

Max Activating Token Index: 970

Text #5

Max Range: 3.4495. Min Range: -3.4495

Max Act: 2.4122. Min Act: -0.0000

Data Index: 110437 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 3.4495. Min Range: -3.4495

Max Act: 2.5331. Min Act: -0.0000

Data Index: 660717 (C4 (Web Text))

Max Activating Token Index: 213

Text #7

Max Range: 3.4495. Min Range: -3.4495

Max Act: 2.2475. Min Act: -0.0000

Data Index: 1106884 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 3.4495. Min Range: -3.4495

Max Act: 2.3538. Min Act: -0.0000

Data Index: 41052 (C4 (Web Text))

Max Activating Token Index: 187

Text #9

Max Range: 3.4495. Min Range: -3.4495

Max Act: 2.5804. Min Act: -0.0000

Data Index: 1207789 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 3.4495. Min Range: -3.4495

Max Act: 2.5767. Min Act: -0.0000

Data Index: 837203 (C4 (Web Text))

Max Activating Token Index: 781

Text #11

Max Range: 3.4495. Min Range: -3.4495

Max Act: 2.1695. Min Act: -0.0000

Data Index: 115473 (C4 (Web Text))

Max Activating Token Index: 357

Text #12

Max Range: 3.4495. Min Range: -3.4495

Max Act: 2.2689. Min Act: -0.0000

Data Index: 270307 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 3.4495. Min Range: -3.4495

Max Act: 2.3467. Min Act: -0.0000

Data Index: 404287 (C4 (Web Text))

Max Activating Token Index: 593

Text #14

Max Range: 3.4495. Min Range: -3.4495

Max Act: 2.3438. Min Act: -0.0000

Data Index: 667227 (C4 (Web Text))

Max Activating Token Index: 862

Text #15

Max Range: 3.4495. Min Range: -3.4495

Max Act: 2.3498. Min Act: -0.0000

Data Index: 1260197 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 3.4495. Min Range: -3.4495

Max Act: 2.2222. Min Act: -0.0000

Data Index: 411756 (C4 (Web Text))

Max Activating Token Index: 464

Text #17

Max Range: 3.4495. Min Range: -3.4495

Max Act: 2.1152. Min Act: -0.0000

Data Index: 412159 (C4 (Web Text))

Max Activating Token Index: 184

Text #18

Max Range: 3.4495. Min Range: -3.4495

Max Act: 2.1938. Min Act: -0.0000

Data Index: 994139 (C4 (Web Text))

Max Activating Token Index: 645

Text #19

Max Range: 3.4495. Min Range: -3.4495

Max Act: 2.0790. Min Act: -0.0000

Data Index: 1015131 (C4 (Web Text))

Max Activating Token Index: 698