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

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

Neuron 2763 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.6240. Min Act: -0.0000

Data Index: 13912 (C4 (Web Text))

Max Activating Token Index: 239

Text #1

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.5154. Min Act: -0.0000

Data Index: 304938 (C4 (Web Text))

Max Activating Token Index: 1003

Text #2

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.4882. Min Act: -0.0000

Data Index: 153453 (C4 (Web Text))

Max Activating Token Index: 239

Text #3

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.4829. Min Act: -0.0000

Data Index: 362100 (C4 (Web Text))

Max Activating Token Index: 884

Text #4

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.4659. Min Act: -0.0000

Data Index: 1204980 (C4 (Web Text))

Max Activating Token Index: 660

Text #5

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.4799. Min Act: -0.0000

Data Index: 1177776 (C4 (Web Text))

Max Activating Token Index: 520

Text #6

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.4769. Min Act: -0.0000

Data Index: 262978 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.4566. Min Act: -0.0000

Data Index: 822866 (C4 (Web Text))

Max Activating Token Index: 373

Text #8

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.4671. Min Act: -0.0000

Data Index: 350667 (C4 (Web Text))

Max Activating Token Index: 531

Text #9

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.4403. Min Act: -0.0000

Data Index: 1164924 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.4551. Min Act: -0.0000

Data Index: 409170 (C4 (Web Text))

Max Activating Token Index: 857

Text #11

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.4665. Min Act: 0.0000

Data Index: 1164266 (C4 (Web Text))

Max Activating Token Index: 526

Text #12

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.4360. Min Act: -0.0000

Data Index: 15330 (C4 (Web Text))

Max Activating Token Index: 631

Text #13

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.4332. Min Act: -0.0000

Data Index: 306839 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.4427. Min Act: -0.0000

Data Index: 1054292 (C4 (Web Text))

Max Activating Token Index: 570

Text #15

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.4646. Min Act: -0.0000

Data Index: 388357 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.4261. Min Act: -0.0000

Data Index: 1057743 (C4 (Web Text))

Max Activating Token Index: 214

Text #17

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.4507. Min Act: -0.0000

Data Index: 875813 (C4 (Web Text))

Max Activating Token Index: 889

Text #18

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.4248. Min Act: -0.0000

Data Index: 257391 (C4 (Web Text))

Max Activating Token Index: 84

Text #19

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.4251. Min Act: -0.0000

Data Index: 860158 (C4 (Web Text))

Max Activating Token Index: 73