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

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

Neuron 1341 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.6361. Min Range: -6.6361

Max Act: 6.6361. Min Act: -0.0000

Data Index: 22587 (C4 (Web Text))

Max Activating Token Index: 809

Text #1

Max Range: 6.6361. Min Range: -6.6361

Max Act: 5.9842. Min Act: -0.0000

Data Index: 798664 (C4 (Web Text))

Max Activating Token Index: 401

Text #2

Max Range: 6.6361. Min Range: -6.6361

Max Act: 5.4215. Min Act: -0.0000

Data Index: 1356516 (C4 (Web Text))

Max Activating Token Index: 1017

Text #3

Max Range: 6.6361. Min Range: -6.6361

Max Act: 5.5248. Min Act: -0.0000

Data Index: 903088 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 6.6361. Min Range: -6.6361

Max Act: 5.2641. Min Act: -0.0000

Data Index: 771647 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 6.6361. Min Range: -6.6361

Max Act: 5.0769. Min Act: -0.0000

Data Index: 318325 (C4 (Web Text))

Max Activating Token Index: 809

Text #6

Max Range: 6.6361. Min Range: -6.6361

Max Act: 5.1897. Min Act: -0.0000

Data Index: 1208450 (C4 (Web Text))

Max Activating Token Index: 927

Text #7

Max Range: 6.6361. Min Range: -6.6361

Max Act: 5.7121. Min Act: -0.0000

Data Index: 1273119 (C4 (Web Text))

Max Activating Token Index: 228

Text #8

Max Range: 6.6361. Min Range: -6.6361

Max Act: 4.9742. Min Act: -0.0000

Data Index: 1343954 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 6.6361. Min Range: -6.6361

Max Act: 5.3555. Min Act: -0.0000

Data Index: 217928 (C4 (Web Text))

Max Activating Token Index: 606

Text #10

Max Range: 6.6361. Min Range: -6.6361

Max Act: 4.9669. Min Act: -0.0000

Data Index: 618077 (C4 (Web Text))

Max Activating Token Index: 873

Text #11

Max Range: 6.6361. Min Range: -6.6361

Max Act: 5.3007. Min Act: -0.0000

Data Index: 1259171 (C4 (Web Text))

Max Activating Token Index: 409

Text #12

Max Range: 6.6361. Min Range: -6.6361

Max Act: 5.0280. Min Act: -0.0000

Data Index: 531023 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 6.6361. Min Range: -6.6361

Max Act: 4.8278. Min Act: -0.0000

Data Index: 799079 (C4 (Web Text))

Max Activating Token Index: 441

Text #14

Max Range: 6.6361. Min Range: -6.6361

Max Act: 5.1858. Min Act: -0.0000

Data Index: 1232433 (C4 (Web Text))

Max Activating Token Index: 590

Text #15

Max Range: 6.6361. Min Range: -6.6361

Max Act: 4.9357. Min Act: -0.0000

Data Index: 1079605 (C4 (Web Text))

Max Activating Token Index: 716

Text #16

Max Range: 6.6361. Min Range: -6.6361

Max Act: 4.7812. Min Act: -0.0000

Data Index: 729783 (C4 (Web Text))

Max Activating Token Index: 338

Text #17

Max Range: 6.6361. Min Range: -6.6361

Max Act: 4.6063. Min Act: -0.0000

Data Index: 1321770 (C4 (Web Text))

Max Activating Token Index: 1010

Text #18

Max Range: 6.6361. Min Range: -6.6361

Max Act: 5.0685. Min Act: -0.0000

Data Index: 921371 (C4 (Web Text))

Max Activating Token Index: 101

Text #19

Max Range: 6.6361. Min Range: -6.6361

Max Act: 4.7068. Min Act: -0.0000

Data Index: 1024678 (C4 (Web Text))

Max Activating Token Index: 62