Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 786 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0466. Min Act: -0.0003

Data Index: 665747 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0432. Min Act: -0.0003

Data Index: 806880 (C4 (Web Text))

Max Activating Token Index: 385

Text #2

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0444. Min Act: -0.0003

Data Index: 88919 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0437. Min Act: -0.0003

Data Index: 1262403 (C4 (Web Text))

Max Activating Token Index: 817

Text #4

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0413. Min Act: -0.0003

Data Index: 549547 (C4 (Web Text))

Max Activating Token Index: 624

Text #5

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0405. Min Act: -0.0003

Data Index: 1061429 (C4 (Web Text))

Max Activating Token Index: 494

Text #6

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0406. Min Act: -0.0003

Data Index: 358000 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0414. Min Act: -0.0003

Data Index: 26823 (C4 (Web Text))

Max Activating Token Index: 289

Text #8

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0383. Min Act: -0.0003

Data Index: 889106 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0382. Min Act: -0.0003

Data Index: 871817 (C4 (Web Text))

Max Activating Token Index: 563

Text #10

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0348. Min Act: -0.0002

Data Index: 1282010 (C4 (Web Text))

Max Activating Token Index: 775

Text #11

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0351. Min Act: -0.0002

Data Index: 1028964 (C4 (Web Text))

Max Activating Token Index: 809

Text #12

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0358. Min Act: -0.0003

Data Index: 995521 (C4 (Web Text))

Max Activating Token Index: 467

Text #13

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0343. Min Act: -0.0002

Data Index: 1181185 (C4 (Web Text))

Max Activating Token Index: 72

Text #14

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0334. Min Act: -0.0003

Data Index: 445970 (C4 (Web Text))

Max Activating Token Index: 30

Text #15

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0345. Min Act: -0.0003

Data Index: 1028920 (C4 (Web Text))

Max Activating Token Index: 24

Text #16

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0340. Min Act: -0.0003

Data Index: 1068063 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0340. Min Act: -0.0003

Data Index: 950728 (C4 (Web Text))

Max Activating Token Index: 668

Text #18

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0299. Min Act: -0.0003

Data Index: 291816 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0327. Min Act: -0.0002

Data Index: 115109 (C4 (Web Text))

Max Activating Token Index: 544