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

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

Neuron 1611 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3637. Min Range: -5.3637

Max Act: 5.2408. Min Act: -0.0000

Data Index: 898584 (C4 (Web Text))

Max Activating Token Index: 361

Text #1

Max Range: 5.3637. Min Range: -5.3637

Max Act: 5.3637. Min Act: -0.0000

Data Index: 1083899 (C4 (Web Text))

Max Activating Token Index: 896

Text #2

Max Range: 5.3637. Min Range: -5.3637

Max Act: 5.3362. Min Act: -0.0000

Data Index: 995225 (C4 (Web Text))

Max Activating Token Index: 62

Text #3

Max Range: 5.3637. Min Range: -5.3637

Max Act: 5.0279. Min Act: -0.0000

Data Index: 449427 (C4 (Web Text))

Max Activating Token Index: 768

Text #4

Max Range: 5.3637. Min Range: -5.3637

Max Act: 5.0283. Min Act: -0.0000

Data Index: 666823 (C4 (Web Text))

Max Activating Token Index: 255

Text #5

Max Range: 5.3637. Min Range: -5.3637

Max Act: 5.1143. Min Act: -0.0000

Data Index: 1148907 (C4 (Web Text))

Max Activating Token Index: 669

Text #6

Max Range: 5.3637. Min Range: -5.3637

Max Act: 5.1419. Min Act: -0.0000

Data Index: 181455 (C4 (Web Text))

Max Activating Token Index: 968

Text #7

Max Range: 5.3637. Min Range: -5.3637

Max Act: 5.0514. Min Act: -0.0000

Data Index: 1111290 (C4 (Web Text))

Max Activating Token Index: 495

Text #8

Max Range: 5.3637. Min Range: -5.3637

Max Act: 4.7231. Min Act: -0.0000

Data Index: 443733 (C4 (Web Text))

Max Activating Token Index: 1020

Text #9

Max Range: 5.3637. Min Range: -5.3637

Max Act: 4.3263. Min Act: -0.0000

Data Index: 408356 (C4 (Web Text))

Max Activating Token Index: 772

Text #10

Max Range: 5.3637. Min Range: -5.3637

Max Act: 4.4140. Min Act: -0.0000

Data Index: 1278002 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 5.3637. Min Range: -5.3637

Max Act: 4.7338. Min Act: -0.0000

Data Index: 833112 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 5.3637. Min Range: -5.3637

Max Act: 4.8886. Min Act: -0.0000

Data Index: 564496 (C4 (Web Text))

Max Activating Token Index: 416

Text #13

Max Range: 5.3637. Min Range: -5.3637

Max Act: 4.4505. Min Act: -0.0000

Data Index: 422343 (C4 (Web Text))

Max Activating Token Index: 952

Text #14

Max Range: 5.3637. Min Range: -5.3637

Max Act: 4.3829. Min Act: -0.0000

Data Index: 870017 (C4 (Web Text))

Max Activating Token Index: 116

Text #15

Max Range: 5.3637. Min Range: -5.3637

Max Act: 4.1687. Min Act: -0.0000

Data Index: 607633 (C4 (Web Text))

Max Activating Token Index: 995

Text #16

Max Range: 5.3637. Min Range: -5.3637

Max Act: 4.1473. Min Act: -0.0000

Data Index: 1054340 (C4 (Web Text))

Max Activating Token Index: 954

Text #17

Max Range: 5.3637. Min Range: -5.3637

Max Act: 3.9564. Min Act: -0.0000

Data Index: 922023 (C4 (Web Text))

Max Activating Token Index: 230

Text #18

Max Range: 5.3637. Min Range: -5.3637

Max Act: 4.1135. Min Act: -0.0000

Data Index: 317368 (C4 (Web Text))

Max Activating Token Index: 468

Text #19

Max Range: 5.3637. Min Range: -5.3637

Max Act: 4.2827. Min Act: -0.0000

Data Index: 1358699 (C4 (Web Text))

Max Activating Token Index: 482