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

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

Neuron 793 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0579. Min Act: -0.0001

Data Index: 133943 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0526. Min Act: -0.0002

Data Index: 1372915 (Python Code)

Max Activating Token Index: 888

Text #2

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0529. Min Act: -0.0001

Data Index: 665080 (C4 (Web Text))

Max Activating Token Index: 462

Text #3

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0517. Min Act: -0.0002

Data Index: 847289 (C4 (Web Text))

Max Activating Token Index: 336

Text #4

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0513. Min Act: -0.0001

Data Index: 1283478 (C4 (Web Text))

Max Activating Token Index: 791

Text #5

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0501. Min Act: -0.0000

Data Index: 1348508 (C4 (Web Text))

Max Activating Token Index: 888

Text #6

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0477. Min Act: -0.0002

Data Index: 544785 (C4 (Web Text))

Max Activating Token Index: 364

Text #7

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0457. Min Act: 0.0001

Data Index: 582085 (C4 (Web Text))

Max Activating Token Index: 269

Text #8

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0458. Min Act: -0.0001

Data Index: 1185087 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0458. Min Act: -0.0001

Data Index: 284626 (C4 (Web Text))

Max Activating Token Index: 330

Text #10

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0433. Min Act: -0.0002

Data Index: 780228 (C4 (Web Text))

Max Activating Token Index: 702

Text #11

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0431. Min Act: -0.0001

Data Index: 668673 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0442. Min Act: -0.0002

Data Index: 1067382 (C4 (Web Text))

Max Activating Token Index: 665

Text #13

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0423. Min Act: -0.0001

Data Index: 900656 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0421. Min Act: -0.0002

Data Index: 231966 (C4 (Web Text))

Max Activating Token Index: 538

Text #15

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0409. Min Act: -0.0002

Data Index: 833145 (C4 (Web Text))

Max Activating Token Index: 270

Text #16

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0402. Min Act: -0.0002

Data Index: 58918 (C4 (Web Text))

Max Activating Token Index: 65

Text #17

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0406. Min Act: -0.0002

Data Index: 249234 (C4 (Web Text))

Max Activating Token Index: 27

Text #18

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0393. Min Act: -0.0001

Data Index: 1117594 (C4 (Web Text))

Max Activating Token Index: 58

Text #19

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0385. Min Act: -0.0001

Data Index: 711796 (C4 (Web Text))

Max Activating Token Index: 864