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

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

Neuron 2147 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7364. Min Range: -1.7364

Max Act: 1.7364. Min Act: -0.0000

Data Index: 200668 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 1.7364. Min Range: -1.7364

Max Act: 1.5133. Min Act: -0.0000

Data Index: 89175 (C4 (Web Text))

Max Activating Token Index: 433

Text #2

Max Range: 1.7364. Min Range: -1.7364

Max Act: 1.5233. Min Act: -0.0000

Data Index: 640439 (C4 (Web Text))

Max Activating Token Index: 503

Text #3

Max Range: 1.7364. Min Range: -1.7364

Max Act: 1.5107. Min Act: -0.0000

Data Index: 57259 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 1.7364. Min Range: -1.7364

Max Act: 1.5011. Min Act: -0.0000

Data Index: 493241 (C4 (Web Text))

Max Activating Token Index: 928

Text #5

Max Range: 1.7364. Min Range: -1.7364

Max Act: 1.5380. Min Act: -0.0000

Data Index: 960275 (C4 (Web Text))

Max Activating Token Index: 839

Text #6

Max Range: 1.7364. Min Range: -1.7364

Max Act: 1.5204. Min Act: -0.0000

Data Index: 92066 (C4 (Web Text))

Max Activating Token Index: 373

Text #7

Max Range: 1.7364. Min Range: -1.7364

Max Act: 1.4410. Min Act: -0.0000

Data Index: 389833 (C4 (Web Text))

Max Activating Token Index: 973

Text #8

Max Range: 1.7364. Min Range: -1.7364

Max Act: 1.4291. Min Act: -0.0000

Data Index: 331374 (C4 (Web Text))

Max Activating Token Index: 581

Text #9

Max Range: 1.7364. Min Range: -1.7364

Max Act: 1.4688. Min Act: -0.0000

Data Index: 504432 (C4 (Web Text))

Max Activating Token Index: 492

Text #10

Max Range: 1.7364. Min Range: -1.7364

Max Act: 1.4102. Min Act: -0.0000

Data Index: 122961 (C4 (Web Text))

Max Activating Token Index: 40

Text #11

Max Range: 1.7364. Min Range: -1.7364

Max Act: 1.4541. Min Act: -0.0001

Data Index: 1105717 (C4 (Web Text))

Max Activating Token Index: 952

Text #12

Max Range: 1.7364. Min Range: -1.7364

Max Act: 1.4446. Min Act: -0.0000

Data Index: 735551 (C4 (Web Text))

Max Activating Token Index: 454

Text #13

Max Range: 1.7364. Min Range: -1.7364

Max Act: 1.3909. Min Act: -0.0000

Data Index: 97829 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 1.7364. Min Range: -1.7364

Max Act: 1.3836. Min Act: -0.0000

Data Index: 322236 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 1.7364. Min Range: -1.7364

Max Act: 1.3353. Min Act: -0.0000

Data Index: 744667 (C4 (Web Text))

Max Activating Token Index: 534

Text #16

Max Range: 1.7364. Min Range: -1.7364

Max Act: 1.4548. Min Act: -0.0000

Data Index: 387849 (C4 (Web Text))

Max Activating Token Index: 841

Text #17

Max Range: 1.7364. Min Range: -1.7364

Max Act: 1.3676. Min Act: -0.0000

Data Index: 3410 (C4 (Web Text))

Max Activating Token Index: 577

Text #18

Max Range: 1.7364. Min Range: -1.7364

Max Act: 1.4032. Min Act: -0.0000

Data Index: 1034894 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 1.7364. Min Range: -1.7364

Max Act: 1.3622. Min Act: -0.0000

Data Index: 45807 (C4 (Web Text))

Max Activating Token Index: 198