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

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

Neuron 4589 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8373. Min Range: -4.8373

Max Act: 4.8373. Min Act: -0.0000

Data Index: 230215 (C4 (Web Text))

Max Activating Token Index: 649

Text #1

Max Range: 4.8373. Min Range: -4.8373

Max Act: 4.0329. Min Act: -0.0000

Data Index: 130708 (C4 (Web Text))

Max Activating Token Index: 893

Text #2

Max Range: 4.8373. Min Range: -4.8373

Max Act: 4.1363. Min Act: -0.0000

Data Index: 302482 (C4 (Web Text))

Max Activating Token Index: 411

Text #3

Max Range: 4.8373. Min Range: -4.8373

Max Act: 3.6109. Min Act: -0.0000

Data Index: 377056 (C4 (Web Text))

Max Activating Token Index: 609

Text #4

Max Range: 4.8373. Min Range: -4.8373

Max Act: 3.7472. Min Act: -0.0000

Data Index: 569572 (C4 (Web Text))

Max Activating Token Index: 973

Text #5

Max Range: 4.8373. Min Range: -4.8373

Max Act: 3.2462. Min Act: -0.0000

Data Index: 1169342 (C4 (Web Text))

Max Activating Token Index: 750

Text #6

Max Range: 4.8373. Min Range: -4.8373

Max Act: 3.6187. Min Act: -0.0000

Data Index: 533613 (C4 (Web Text))

Max Activating Token Index: 195

Text #7

Max Range: 4.8373. Min Range: -4.8373

Max Act: 3.4162. Min Act: -0.0000

Data Index: 195532 (C4 (Web Text))

Max Activating Token Index: 282

Text #8

Max Range: 4.8373. Min Range: -4.8373

Max Act: 3.5445. Min Act: -0.0000

Data Index: 1331931 (C4 (Web Text))

Max Activating Token Index: 68

Text #9

Max Range: 4.8373. Min Range: -4.8373

Max Act: 3.3693. Min Act: -0.0000

Data Index: 207364 (C4 (Web Text))

Max Activating Token Index: 823

Text #10

Max Range: 4.8373. Min Range: -4.8373

Max Act: 3.1894. Min Act: -0.0000

Data Index: 483769 (C4 (Web Text))

Max Activating Token Index: 498

Text #11

Max Range: 4.8373. Min Range: -4.8373

Max Act: 3.2296. Min Act: -0.0000

Data Index: 9429 (C4 (Web Text))

Max Activating Token Index: 562

Text #12

Max Range: 4.8373. Min Range: -4.8373

Max Act: 3.1213. Min Act: -0.0000

Data Index: 995266 (C4 (Web Text))

Max Activating Token Index: 606

Text #13

Max Range: 4.8373. Min Range: -4.8373

Max Act: 3.1760. Min Act: -0.0000

Data Index: 1224255 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 4.8373. Min Range: -4.8373

Max Act: 3.2041. Min Act: -0.0000

Data Index: 758017 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 4.8373. Min Range: -4.8373

Max Act: 3.1968. Min Act: -0.0000

Data Index: 627416 (C4 (Web Text))

Max Activating Token Index: 502

Text #16

Max Range: 4.8373. Min Range: -4.8373

Max Act: 3.1853. Min Act: -0.0000

Data Index: 329404 (C4 (Web Text))

Max Activating Token Index: 783

Text #17

Max Range: 4.8373. Min Range: -4.8373

Max Act: 3.1349. Min Act: -0.0000

Data Index: 823118 (C4 (Web Text))

Max Activating Token Index: 412

Text #18

Max Range: 4.8373. Min Range: -4.8373

Max Act: 2.8804. Min Act: -0.0000

Data Index: 1070420 (C4 (Web Text))

Max Activating Token Index: 850

Text #19

Max Range: 4.8373. Min Range: -4.8373

Max Act: 3.1666. Min Act: -0.0000

Data Index: 129275 (C4 (Web Text))

Max Activating Token Index: 370