Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2986 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.9429. Min Act: -0.0001

Data Index: 264141 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.9242. Min Act: -0.0001

Data Index: 1150088 (C4 (Web Text))

Max Activating Token Index: 782

Text #2

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.8965. Min Act: -0.0002

Data Index: 831419 (C4 (Web Text))

Max Activating Token Index: 777

Text #3

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.8212. Min Act: -0.0002

Data Index: 133681 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.8102. Min Act: -0.0002

Data Index: 158178 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.8167. Min Act: -0.0002

Data Index: 613175 (C4 (Web Text))

Max Activating Token Index: 751

Text #6

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.7922. Min Act: -0.0002

Data Index: 842198 (C4 (Web Text))

Max Activating Token Index: 1008

Text #7

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.6177. Min Act: -0.0002

Data Index: 418571 (C4 (Web Text))

Max Activating Token Index: 308

Text #8

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.7475. Min Act: -0.0001

Data Index: 793758 (C4 (Web Text))

Max Activating Token Index: 874

Text #9

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.7657. Min Act: -0.0002

Data Index: 561463 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.6695. Min Act: -0.0001

Data Index: 182676 (C4 (Web Text))

Max Activating Token Index: 182

Text #11

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.7067. Min Act: -0.0002

Data Index: 725998 (C4 (Web Text))

Max Activating Token Index: 544

Text #12

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.7455. Min Act: -0.0002

Data Index: 1117347 (C4 (Web Text))

Max Activating Token Index: 484

Text #13

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.7165. Min Act: -0.0001

Data Index: 197590 (C4 (Web Text))

Max Activating Token Index: 589

Text #14

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.7212. Min Act: -0.0001

Data Index: 825176 (C4 (Web Text))

Max Activating Token Index: 715

Text #15

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.8358. Min Act: -0.0001

Data Index: 718000 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.6985. Min Act: -0.0002

Data Index: 349076 (C4 (Web Text))

Max Activating Token Index: 957

Text #17

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.7913. Min Act: -0.0001

Data Index: 1349793 (C4 (Web Text))

Max Activating Token Index: 660

Text #18

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.7766. Min Act: -0.0002

Data Index: 748264 (C4 (Web Text))

Max Activating Token Index: 165

Text #19

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.7181. Min Act: -0.0002

Data Index: 620181 (C4 (Web Text))

Max Activating Token Index: 782