Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2857 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.1152. Min Range: -4.1152

Max Act: 3.6414. Min Act: -0.0000

Data Index: 1094538 (C4 (Web Text))

Max Activating Token Index: 124

Text #1

Max Range: 4.1152. Min Range: -4.1152

Max Act: 3.1216. Min Act: -0.0000

Data Index: 789628 (C4 (Web Text))

Max Activating Token Index: 554

Text #2

Max Range: 4.1152. Min Range: -4.1152

Max Act: 4.1152. Min Act: -0.0000

Data Index: 1556805 (Python Code)

Max Activating Token Index: 608

Text #3

Max Range: 4.1152. Min Range: -4.1152

Max Act: 3.5049. Min Act: -0.0000

Data Index: 580874 (C4 (Web Text))

Max Activating Token Index: 789

Text #4

Max Range: 4.1152. Min Range: -4.1152

Max Act: 3.1503. Min Act: -0.0000

Data Index: 81364 (C4 (Web Text))

Max Activating Token Index: 861

Text #5

Max Range: 4.1152. Min Range: -4.1152

Max Act: 3.2989. Min Act: -0.0000

Data Index: 586201 (C4 (Web Text))

Max Activating Token Index: 110

Text #6

Max Range: 4.1152. Min Range: -4.1152

Max Act: 3.3232. Min Act: -0.0000

Data Index: 1410546 (Python Code)

Max Activating Token Index: 586

Text #7

Max Range: 4.1152. Min Range: -4.1152

Max Act: 2.8569. Min Act: -0.0000

Data Index: 496255 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 4.1152. Min Range: -4.1152

Max Act: 3.2451. Min Act: -0.0000

Data Index: 1031705 (C4 (Web Text))

Max Activating Token Index: 593

Text #9

Max Range: 4.1152. Min Range: -4.1152

Max Act: 3.1602. Min Act: -0.0000

Data Index: 1280606 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 4.1152. Min Range: -4.1152

Max Act: 3.1188. Min Act: -0.0000

Data Index: 1426974 (Python Code)

Max Activating Token Index: 192

Text #11

Max Range: 4.1152. Min Range: -4.1152

Max Act: 3.2810. Min Act: -0.0000

Data Index: 996075 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 4.1152. Min Range: -4.1152

Max Act: 3.0768. Min Act: -0.0000

Data Index: 1451410 (Python Code)

Max Activating Token Index: 564

Text #13

Max Range: 4.1152. Min Range: -4.1152

Max Act: 2.6798. Min Act: -0.0000

Data Index: 1222424 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 4.1152. Min Range: -4.1152

Max Act: 3.0399. Min Act: -0.0000

Data Index: 1419732 (Python Code)

Max Activating Token Index: 822

Text #15

Max Range: 4.1152. Min Range: -4.1152

Max Act: 2.8846. Min Act: -0.0000

Data Index: 544343 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 4.1152. Min Range: -4.1152

Max Act: 2.6194. Min Act: -0.0000

Data Index: 336695 (C4 (Web Text))

Max Activating Token Index: 643

Text #17

Max Range: 4.1152. Min Range: -4.1152

Max Act: 2.8668. Min Act: -0.0000

Data Index: 1560508 (Python Code)

Max Activating Token Index: 64

Text #18

Max Range: 4.1152. Min Range: -4.1152

Max Act: 3.4069. Min Act: -0.0000

Data Index: 1413661 (Python Code)

Max Activating Token Index: 145

Text #19

Max Range: 4.1152. Min Range: -4.1152

Max Act: 2.8247. Min Act: -0.0000

Data Index: 1010510 (C4 (Web Text))

Max Activating Token Index: 919