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

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

Neuron 5856 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.6365. Min Act: -0.0000

Data Index: 505145 (C4 (Web Text))

Max Activating Token Index: 633

Text #1

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.4638. Min Act: -0.0000

Data Index: 336902 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.4495. Min Act: -0.0000

Data Index: 1076408 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.4486. Min Act: -0.0000

Data Index: 413403 (C4 (Web Text))

Max Activating Token Index: 652

Text #4

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.4504. Min Act: -0.0000

Data Index: 463341 (C4 (Web Text))

Max Activating Token Index: 628

Text #5

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.2683. Min Act: -0.0000

Data Index: 259178 (C4 (Web Text))

Max Activating Token Index: 265

Text #6

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.2451. Min Act: -0.0000

Data Index: 948052 (C4 (Web Text))

Max Activating Token Index: 884

Text #7

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.3185. Min Act: -0.0000

Data Index: 1275178 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.3270. Min Act: -0.0000

Data Index: 996202 (C4 (Web Text))

Max Activating Token Index: 522

Text #9

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.5000. Min Act: -0.0000

Data Index: 1280558 (C4 (Web Text))

Max Activating Token Index: 441

Text #10

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.3100. Min Act: -0.0000

Data Index: 25431 (C4 (Web Text))

Max Activating Token Index: 360

Text #11

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.1715. Min Act: -0.0000

Data Index: 976289 (C4 (Web Text))

Max Activating Token Index: 283

Text #12

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.3007. Min Act: -0.0000

Data Index: 43917 (C4 (Web Text))

Max Activating Token Index: 335

Text #13

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.2969. Min Act: -0.0000

Data Index: 637859 (C4 (Web Text))

Max Activating Token Index: 480

Text #14

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.2768. Min Act: -0.0000

Data Index: 1350391 (C4 (Web Text))

Max Activating Token Index: 710

Text #15

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.3858. Min Act: -0.0000

Data Index: 983403 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.4084. Min Act: -0.0000

Data Index: 567503 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.3659. Min Act: -0.0000

Data Index: 191373 (C4 (Web Text))

Max Activating Token Index: 910

Text #18

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.2402. Min Act: -0.0000

Data Index: 67328 (C4 (Web Text))

Max Activating Token Index: 717

Text #19

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.0812. Min Act: -0.0000

Data Index: 416031 (C4 (Web Text))

Max Activating Token Index: 842