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

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

Neuron 4145 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.2631. Min Range: -1.2631

Max Act: 1.2631. Min Act: -0.0002

Data Index: 305974 (C4 (Web Text))

Max Activating Token Index: 416

Text #1

Max Range: 1.2631. Min Range: -1.2631

Max Act: 1.2546. Min Act: -0.0002

Data Index: 597915 (C4 (Web Text))

Max Activating Token Index: 595

Text #2

Max Range: 1.2631. Min Range: -1.2631

Max Act: 1.2001. Min Act: -0.0003

Data Index: 405716 (C4 (Web Text))

Max Activating Token Index: 752

Text #3

Max Range: 1.2631. Min Range: -1.2631

Max Act: 1.1375. Min Act: -0.0002

Data Index: 1061387 (C4 (Web Text))

Max Activating Token Index: 185

Text #4

Max Range: 1.2631. Min Range: -1.2631

Max Act: 1.1268. Min Act: -0.0002

Data Index: 446029 (C4 (Web Text))

Max Activating Token Index: 848

Text #5

Max Range: 1.2631. Min Range: -1.2631

Max Act: 1.1074. Min Act: -0.0003

Data Index: 355960 (C4 (Web Text))

Max Activating Token Index: 821

Text #6

Max Range: 1.2631. Min Range: -1.2631

Max Act: 1.1257. Min Act: -0.0002

Data Index: 707778 (C4 (Web Text))

Max Activating Token Index: 335

Text #7

Max Range: 1.2631. Min Range: -1.2631

Max Act: 1.0769. Min Act: -0.0003

Data Index: 584687 (C4 (Web Text))

Max Activating Token Index: 874

Text #8

Max Range: 1.2631. Min Range: -1.2631

Max Act: 1.0619. Min Act: -0.0002

Data Index: 420406 (C4 (Web Text))

Max Activating Token Index: 701

Text #9

Max Range: 1.2631. Min Range: -1.2631

Max Act: 1.0498. Min Act: -0.0002

Data Index: 771450 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 1.2631. Min Range: -1.2631

Max Act: 1.0512. Min Act: -0.0002

Data Index: 784548 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 1.2631. Min Range: -1.2631

Max Act: 1.0600. Min Act: -0.0003

Data Index: 867384 (C4 (Web Text))

Max Activating Token Index: 269

Text #12

Max Range: 1.2631. Min Range: -1.2631

Max Act: 1.0481. Min Act: -0.0002

Data Index: 939484 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 1.2631. Min Range: -1.2631

Max Act: 1.0464. Min Act: -0.0002

Data Index: 30490 (C4 (Web Text))

Max Activating Token Index: 544

Text #14

Max Range: 1.2631. Min Range: -1.2631

Max Act: 1.0322. Min Act: -0.0002

Data Index: 54961 (C4 (Web Text))

Max Activating Token Index: 191

Text #15

Max Range: 1.2631. Min Range: -1.2631

Max Act: 1.0305. Min Act: -0.0002

Data Index: 1358079 (C4 (Web Text))

Max Activating Token Index: 808

Text #16

Max Range: 1.2631. Min Range: -1.2631

Max Act: 1.0270. Min Act: -0.0002

Data Index: 1279664 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 1.2631. Min Range: -1.2631

Max Act: 1.0280. Min Act: -0.0002

Data Index: 273658 (C4 (Web Text))

Max Activating Token Index: 974

Text #18

Max Range: 1.2631. Min Range: -1.2631

Max Act: 1.0342. Min Act: -0.0003

Data Index: 1069941 (C4 (Web Text))

Max Activating Token Index: 140

Text #19

Max Range: 1.2631. Min Range: -1.2631

Max Act: 1.0324. Min Act: -0.0002

Data Index: 1147964 (C4 (Web Text))

Max Activating Token Index: 334