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

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

Neuron 1226 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5973. Min Range: -2.5973

Max Act: 2.5973. Min Act: -0.0000

Data Index: 285378 (C4 (Web Text))

Max Activating Token Index: 798

Text #1

Max Range: 2.5973. Min Range: -2.5973

Max Act: 2.3683. Min Act: -0.0001

Data Index: 147239 (C4 (Web Text))

Max Activating Token Index: 785

Text #2

Max Range: 2.5973. Min Range: -2.5973

Max Act: 1.9847. Min Act: -0.0000

Data Index: 1058437 (C4 (Web Text))

Max Activating Token Index: 513

Text #3

Max Range: 2.5973. Min Range: -2.5973

Max Act: 1.8935. Min Act: -0.0000

Data Index: 1119158 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 2.5973. Min Range: -2.5973

Max Act: 1.9780. Min Act: -0.0001

Data Index: 220331 (C4 (Web Text))

Max Activating Token Index: 341

Text #5

Max Range: 2.5973. Min Range: -2.5973

Max Act: 1.8650. Min Act: -0.0000

Data Index: 850884 (C4 (Web Text))

Max Activating Token Index: 505

Text #6

Max Range: 2.5973. Min Range: -2.5973

Max Act: 1.7271. Min Act: -0.0001

Data Index: 473122 (C4 (Web Text))

Max Activating Token Index: 871

Text #7

Max Range: 2.5973. Min Range: -2.5973

Max Act: 1.8575. Min Act: -0.0001

Data Index: 84252 (C4 (Web Text))

Max Activating Token Index: 406

Text #8

Max Range: 2.5973. Min Range: -2.5973

Max Act: 1.7009. Min Act: -0.0001

Data Index: 807451 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 2.5973. Min Range: -2.5973

Max Act: 1.7468. Min Act: -0.0001

Data Index: 148340 (C4 (Web Text))

Max Activating Token Index: 307

Text #10

Max Range: 2.5973. Min Range: -2.5973

Max Act: 1.7505. Min Act: -0.0000

Data Index: 1304160 (C4 (Web Text))

Max Activating Token Index: 470

Text #11

Max Range: 2.5973. Min Range: -2.5973

Max Act: 1.5701. Min Act: -0.0001

Data Index: 1061911 (C4 (Web Text))

Max Activating Token Index: 389

Text #12

Max Range: 2.5973. Min Range: -2.5973

Max Act: 1.5977. Min Act: -0.0001

Data Index: 410989 (C4 (Web Text))

Max Activating Token Index: 484

Text #13

Max Range: 2.5973. Min Range: -2.5973

Max Act: 1.7268. Min Act: -0.0000

Data Index: 530310 (C4 (Web Text))

Max Activating Token Index: 413

Text #14

Max Range: 2.5973. Min Range: -2.5973

Max Act: 1.6874. Min Act: -0.0000

Data Index: 789606 (C4 (Web Text))

Max Activating Token Index: 624

Text #15

Max Range: 2.5973. Min Range: -2.5973

Max Act: 1.4773. Min Act: -0.0000

Data Index: 209248 (C4 (Web Text))

Max Activating Token Index: 166

Text #16

Max Range: 2.5973. Min Range: -2.5973

Max Act: 1.5373. Min Act: -0.0000

Data Index: 724480 (C4 (Web Text))

Max Activating Token Index: 811

Text #17

Max Range: 2.5973. Min Range: -2.5973

Max Act: 1.5847. Min Act: -0.0001

Data Index: 520873 (C4 (Web Text))

Max Activating Token Index: 623

Text #18

Max Range: 2.5973. Min Range: -2.5973

Max Act: 1.6198. Min Act: -0.0000

Data Index: 1357576 (C4 (Web Text))

Max Activating Token Index: 853

Text #19

Max Range: 2.5973. Min Range: -2.5973

Max Act: 1.5439. Min Act: -0.0000

Data Index: 1253324 (C4 (Web Text))

Max Activating Token Index: 559