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

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

Neuron 1897 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.6411. Min Act: -0.0000

Data Index: 526179 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.5911. Min Act: -0.0000

Data Index: 798436 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.5230. Min Act: -0.0000

Data Index: 446673 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.4788. Min Act: -0.0000

Data Index: 363254 (C4 (Web Text))

Max Activating Token Index: 602

Text #4

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.4682. Min Act: -0.0000

Data Index: 543815 (C4 (Web Text))

Max Activating Token Index: 863

Text #5

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.4319. Min Act: -0.0000

Data Index: 523205 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.4223. Min Act: -0.0000

Data Index: 805347 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.4172. Min Act: -0.0000

Data Index: 37746 (C4 (Web Text))

Max Activating Token Index: 934

Text #8

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.3980. Min Act: -0.0000

Data Index: 492027 (C4 (Web Text))

Max Activating Token Index: 748

Text #9

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.3892. Min Act: 0.0000

Data Index: 247410 (C4 (Web Text))

Max Activating Token Index: 413

Text #10

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.4134. Min Act: -0.0000

Data Index: 690048 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.3826. Min Act: -0.0000

Data Index: 97367 (C4 (Web Text))

Max Activating Token Index: 645

Text #12

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.3725. Min Act: -0.0000

Data Index: 66541 (C4 (Web Text))

Max Activating Token Index: 372

Text #13

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.3674. Min Act: -0.0000

Data Index: 800891 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.3772. Min Act: -0.0000

Data Index: 293230 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.3772. Min Act: -0.0000

Data Index: 1061833 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.3737. Min Act: -0.0000

Data Index: 956847 (C4 (Web Text))

Max Activating Token Index: 782

Text #17

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.3599. Min Act: -0.0000

Data Index: 1038388 (C4 (Web Text))

Max Activating Token Index: 519

Text #18

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.3466. Min Act: -0.0000

Data Index: 1016770 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.3719. Min Act: -0.0000

Data Index: 1263064 (C4 (Web Text))

Max Activating Token Index: 718