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

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

Neuron 3 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.4781. Min Act: -0.0000

Data Index: 199045 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.4830. Min Act: -0.0000

Data Index: 699907 (C4 (Web Text))

Max Activating Token Index: 211

Text #2

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.4663. Min Act: -0.0000

Data Index: 668304 (C4 (Web Text))

Max Activating Token Index: 340

Text #3

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.4671. Min Act: -0.0000

Data Index: 730248 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.4413. Min Act: -0.0000

Data Index: 1158797 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.4418. Min Act: -0.0000

Data Index: 742382 (C4 (Web Text))

Max Activating Token Index: 366

Text #6

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.4322. Min Act: -0.0000

Data Index: 1234535 (C4 (Web Text))

Max Activating Token Index: 568

Text #7

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.4445. Min Act: -0.0000

Data Index: 264284 (C4 (Web Text))

Max Activating Token Index: 378

Text #8

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.3873. Min Act: -0.0000

Data Index: 1038429 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.4193. Min Act: -0.0000

Data Index: 13302 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.4084. Min Act: -0.0000

Data Index: 874282 (C4 (Web Text))

Max Activating Token Index: 344

Text #11

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.4291. Min Act: -0.0000

Data Index: 1278131 (C4 (Web Text))

Max Activating Token Index: 103

Text #12

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.4373. Min Act: -0.0000

Data Index: 96627 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.4204. Min Act: -0.0000

Data Index: 1337955 (C4 (Web Text))

Max Activating Token Index: 650

Text #14

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.4360. Min Act: -0.0000

Data Index: 645992 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.4203. Min Act: -0.0000

Data Index: 771926 (C4 (Web Text))

Max Activating Token Index: 115

Text #16

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.4472. Min Act: -0.0000

Data Index: 503432 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.4143. Min Act: -0.0000

Data Index: 538858 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.3981. Min Act: -0.0000

Data Index: 62435 (C4 (Web Text))

Max Activating Token Index: 271

Text #19

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.4133. Min Act: -0.0000

Data Index: 431391 (C4 (Web Text))

Max Activating Token Index: 911