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

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

Neuron 5113 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5289. Min Range: -0.5289

Max Act: 0.5289. Min Act: -0.0000

Data Index: 56423 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 0.5289. Min Range: -0.5289

Max Act: 0.5276. Min Act: -0.0000

Data Index: 964513 (C4 (Web Text))

Max Activating Token Index: 802

Text #2

Max Range: 0.5289. Min Range: -0.5289

Max Act: 0.5280. Min Act: -0.0000

Data Index: 719770 (C4 (Web Text))

Max Activating Token Index: 860

Text #3

Max Range: 0.5289. Min Range: -0.5289

Max Act: 0.5065. Min Act: -0.0000

Data Index: 28506 (C4 (Web Text))

Max Activating Token Index: 682

Text #4

Max Range: 0.5289. Min Range: -0.5289

Max Act: 0.5010. Min Act: -0.0000

Data Index: 580695 (C4 (Web Text))

Max Activating Token Index: 480

Text #5

Max Range: 0.5289. Min Range: -0.5289

Max Act: 0.4625. Min Act: -0.0000

Data Index: 285102 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 0.5289. Min Range: -0.5289

Max Act: 0.4123. Min Act: -0.0000

Data Index: 49336 (C4 (Web Text))

Max Activating Token Index: 556

Text #7

Max Range: 0.5289. Min Range: -0.5289

Max Act: 0.4087. Min Act: -0.0000

Data Index: 1292410 (C4 (Web Text))

Max Activating Token Index: 398

Text #8

Max Range: 0.5289. Min Range: -0.5289

Max Act: 0.4087. Min Act: -0.0000

Data Index: 507860 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 0.5289. Min Range: -0.5289

Max Act: 0.4417. Min Act: -0.0000

Data Index: 1033203 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 0.5289. Min Range: -0.5289

Max Act: 0.3763. Min Act: -0.0000

Data Index: 180368 (C4 (Web Text))

Max Activating Token Index: 285

Text #11

Max Range: 0.5289. Min Range: -0.5289

Max Act: 0.3779. Min Act: -0.0000

Data Index: 96929 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 0.5289. Min Range: -0.5289

Max Act: 0.3779. Min Act: -0.0000

Data Index: 962177 (C4 (Web Text))

Max Activating Token Index: 1007

Text #13

Max Range: 0.5289. Min Range: -0.5289

Max Act: 0.3993. Min Act: -0.0000

Data Index: 1028603 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 0.5289. Min Range: -0.5289

Max Act: 0.3781. Min Act: -0.0000

Data Index: 295258 (C4 (Web Text))

Max Activating Token Index: 756

Text #15

Max Range: 0.5289. Min Range: -0.5289

Max Act: 0.3535. Min Act: -0.0000

Data Index: 1357103 (C4 (Web Text))

Max Activating Token Index: 829

Text #16

Max Range: 0.5289. Min Range: -0.5289

Max Act: 0.3857. Min Act: -0.0000

Data Index: 14785 (C4 (Web Text))

Max Activating Token Index: 272

Text #17

Max Range: 0.5289. Min Range: -0.5289

Max Act: 0.3661. Min Act: -0.0000

Data Index: 1241986 (C4 (Web Text))

Max Activating Token Index: 923

Text #18

Max Range: 0.5289. Min Range: -0.5289

Max Act: 0.3409. Min Act: -0.0000

Data Index: 494486 (C4 (Web Text))

Max Activating Token Index: 656

Text #19

Max Range: 0.5289. Min Range: -0.5289

Max Act: 0.3502. Min Act: -0.0000

Data Index: 1232876 (C4 (Web Text))

Max Activating Token Index: 789