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

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

Neuron 923 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0798. Min Act: -0.0002

Data Index: 414983 (C4 (Web Text))

Max Activating Token Index: 721

Text #1

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0754. Min Act: -0.0002

Data Index: 588481 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0673. Min Act: -0.0002

Data Index: 1147129 (C4 (Web Text))

Max Activating Token Index: 297

Text #3

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0670. Min Act: -0.0002

Data Index: 254748 (C4 (Web Text))

Max Activating Token Index: 875

Text #4

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0620. Min Act: -0.0002

Data Index: 930871 (C4 (Web Text))

Max Activating Token Index: 319

Text #5

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0598. Min Act: -0.0002

Data Index: 18878 (C4 (Web Text))

Max Activating Token Index: 695

Text #6

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0562. Min Act: -0.0002

Data Index: 490123 (C4 (Web Text))

Max Activating Token Index: 498

Text #7

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0576. Min Act: -0.0002

Data Index: 892819 (C4 (Web Text))

Max Activating Token Index: 801

Text #8

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0505. Min Act: -0.0002

Data Index: 1084429 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0488. Min Act: -0.0002

Data Index: 552506 (C4 (Web Text))

Max Activating Token Index: 359

Text #10

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0493. Min Act: -0.0002

Data Index: 1075793 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0463. Min Act: -0.0002

Data Index: 1165072 (C4 (Web Text))

Max Activating Token Index: 101

Text #12

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0434. Min Act: -0.0002

Data Index: 320881 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0432. Min Act: -0.0002

Data Index: 99068 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0395. Min Act: -0.0002

Data Index: 150167 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0386. Min Act: -0.0002

Data Index: 918206 (C4 (Web Text))

Max Activating Token Index: 455

Text #16

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0382. Min Act: -0.0002

Data Index: 834165 (C4 (Web Text))

Max Activating Token Index: 501

Text #17

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0377. Min Act: -0.0002

Data Index: 253509 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0370. Min Act: -0.0002

Data Index: 766290 (C4 (Web Text))

Max Activating Token Index: 670

Text #19

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0353. Min Act: -0.0002

Data Index: 451710 (C4 (Web Text))

Max Activating Token Index: 66