Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 795 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.3640. Min Act: -0.0001

Data Index: 729377 (C4 (Web Text))

Max Activating Token Index: 605

Text #1

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.3402. Min Act: -0.0001

Data Index: 379498 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.3410. Min Act: -0.0001

Data Index: 78049 (C4 (Web Text))

Max Activating Token Index: 984

Text #3

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.3529. Min Act: -0.0001

Data Index: 1354999 (C4 (Web Text))

Max Activating Token Index: 321

Text #4

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.3225. Min Act: -0.0001

Data Index: 391009 (C4 (Web Text))

Max Activating Token Index: 377

Text #5

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.3281. Min Act: -0.0001

Data Index: 431419 (C4 (Web Text))

Max Activating Token Index: 818

Text #6

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.3276. Min Act: -0.0001

Data Index: 609683 (C4 (Web Text))

Max Activating Token Index: 138

Text #7

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.3395. Min Act: -0.0001

Data Index: 260907 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.3245. Min Act: -0.0001

Data Index: 148033 (C4 (Web Text))

Max Activating Token Index: 566

Text #9

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.3212. Min Act: -0.0001

Data Index: 581269 (C4 (Web Text))

Max Activating Token Index: 824

Text #10

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.3228. Min Act: -0.0001

Data Index: 499222 (C4 (Web Text))

Max Activating Token Index: 339

Text #11

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.3180. Min Act: -0.0001

Data Index: 493181 (C4 (Web Text))

Max Activating Token Index: 391

Text #12

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.3099. Min Act: -0.0001

Data Index: 1073047 (C4 (Web Text))

Max Activating Token Index: 587

Text #13

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.3244. Min Act: -0.0001

Data Index: 382663 (C4 (Web Text))

Max Activating Token Index: 407

Text #14

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.2888. Min Act: -0.0001

Data Index: 365108 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.3204. Min Act: -0.0001

Data Index: 792273 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.3151. Min Act: -0.0001

Data Index: 1168237 (C4 (Web Text))

Max Activating Token Index: 848

Text #17

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.3047. Min Act: -0.0001

Data Index: 578733 (C4 (Web Text))

Max Activating Token Index: 583

Text #18

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.2820. Min Act: -0.0001

Data Index: 716548 (C4 (Web Text))

Max Activating Token Index: 846

Text #19

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.2887. Min Act: -0.0001

Data Index: 348663 (C4 (Web Text))

Max Activating Token Index: 858