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

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

Neuron 3736 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0899. Min Range: -3.0899

Max Act: 3.0899. Min Act: -0.0000

Data Index: 482291 (C4 (Web Text))

Max Activating Token Index: 462

Text #1

Max Range: 3.0899. Min Range: -3.0899

Max Act: 2.8668. Min Act: -0.0000

Data Index: 493817 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 3.0899. Min Range: -3.0899

Max Act: 2.8344. Min Act: -0.0000

Data Index: 946634 (C4 (Web Text))

Max Activating Token Index: 327

Text #3

Max Range: 3.0899. Min Range: -3.0899

Max Act: 2.7145. Min Act: -0.0000

Data Index: 940169 (C4 (Web Text))

Max Activating Token Index: 779

Text #4

Max Range: 3.0899. Min Range: -3.0899

Max Act: 2.5291. Min Act: -0.0000

Data Index: 614707 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 3.0899. Min Range: -3.0899

Max Act: 2.3971. Min Act: -0.0000

Data Index: 1209278 (C4 (Web Text))

Max Activating Token Index: 639

Text #6

Max Range: 3.0899. Min Range: -3.0899

Max Act: 2.3314. Min Act: -0.0000

Data Index: 1304407 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 3.0899. Min Range: -3.0899

Max Act: 2.4490. Min Act: -0.0000

Data Index: 872164 (C4 (Web Text))

Max Activating Token Index: 765

Text #8

Max Range: 3.0899. Min Range: -3.0899

Max Act: 2.1641. Min Act: -0.0000

Data Index: 386395 (C4 (Web Text))

Max Activating Token Index: 504

Text #9

Max Range: 3.0899. Min Range: -3.0899

Max Act: 2.2075. Min Act: -0.0000

Data Index: 494450 (C4 (Web Text))

Max Activating Token Index: 272

Text #10

Max Range: 3.0899. Min Range: -3.0899

Max Act: 2.1981. Min Act: -0.0000

Data Index: 579034 (C4 (Web Text))

Max Activating Token Index: 257

Text #11

Max Range: 3.0899. Min Range: -3.0899

Max Act: 2.1277. Min Act: -0.0000

Data Index: 1288092 (C4 (Web Text))

Max Activating Token Index: 687

Text #12

Max Range: 3.0899. Min Range: -3.0899

Max Act: 2.0898. Min Act: -0.0000

Data Index: 1181321 (C4 (Web Text))

Max Activating Token Index: 425

Text #13

Max Range: 3.0899. Min Range: -3.0899

Max Act: 2.1141. Min Act: -0.0000

Data Index: 1543813 (Python Code)

Max Activating Token Index: 118

Text #14

Max Range: 3.0899. Min Range: -3.0899

Max Act: 1.9760. Min Act: -0.0000

Data Index: 1095428 (C4 (Web Text))

Max Activating Token Index: 995

Text #15

Max Range: 3.0899. Min Range: -3.0899

Max Act: 2.0022. Min Act: -0.0000

Data Index: 313471 (C4 (Web Text))

Max Activating Token Index: 702

Text #16

Max Range: 3.0899. Min Range: -3.0899

Max Act: 1.8759. Min Act: -0.0000

Data Index: 1311113 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 3.0899. Min Range: -3.0899

Max Act: 2.0509. Min Act: -0.0000

Data Index: 493698 (C4 (Web Text))

Max Activating Token Index: 999

Text #18

Max Range: 3.0899. Min Range: -3.0899

Max Act: 1.8454. Min Act: -0.0000

Data Index: 367478 (C4 (Web Text))

Max Activating Token Index: 495

Text #19

Max Range: 3.0899. Min Range: -3.0899

Max Act: 1.9027. Min Act: -0.0000

Data Index: 1007505 (C4 (Web Text))

Max Activating Token Index: 196