Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2301 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0846. Min Act: -0.0001

Data Index: 1062568 (C4 (Web Text))

Max Activating Token Index: 273

Text #1

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0645. Min Act: -0.0001

Data Index: 391893 (C4 (Web Text))

Max Activating Token Index: 903

Text #2

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0586. Min Act: -0.0001

Data Index: 149189 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0508. Min Act: -0.0001

Data Index: 396095 (C4 (Web Text))

Max Activating Token Index: 358

Text #4

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0512. Min Act: -0.0001

Data Index: 1139928 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0455. Min Act: -0.0001

Data Index: 1335433 (C4 (Web Text))

Max Activating Token Index: 610

Text #6

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0493. Min Act: -0.0001

Data Index: 951960 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0444. Min Act: -0.0001

Data Index: 573638 (C4 (Web Text))

Max Activating Token Index: 904

Text #8

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0449. Min Act: -0.0001

Data Index: 1310824 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0451. Min Act: -0.0001

Data Index: 1300089 (C4 (Web Text))

Max Activating Token Index: 183

Text #10

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0417. Min Act: -0.0001

Data Index: 243182 (C4 (Web Text))

Max Activating Token Index: 874

Text #11

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0427. Min Act: -0.0001

Data Index: 919636 (C4 (Web Text))

Max Activating Token Index: 368

Text #12

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0434. Min Act: -0.0001

Data Index: 1187397 (C4 (Web Text))

Max Activating Token Index: 638

Text #13

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0428. Min Act: -0.0001

Data Index: 398189 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0395. Min Act: -0.0001

Data Index: 938343 (C4 (Web Text))

Max Activating Token Index: 381

Text #15

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0376. Min Act: -0.0001

Data Index: 940683 (C4 (Web Text))

Max Activating Token Index: 927

Text #16

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0346. Min Act: -0.0001

Data Index: 635720 (C4 (Web Text))

Max Activating Token Index: 539

Text #17

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0383. Min Act: -0.0001

Data Index: 590784 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0398. Min Act: -0.0001

Data Index: 409918 (C4 (Web Text))

Max Activating Token Index: 65

Text #19

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0331. Min Act: -0.0001

Data Index: 827574 (C4 (Web Text))

Max Activating Token Index: 964