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

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

Neuron 924 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0466. Min Range: -2.0466

Max Act: 2.0466. Min Act: -0.0000

Data Index: 424081 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 2.0466. Min Range: -2.0466

Max Act: 1.9959. Min Act: -0.0000

Data Index: 1298551 (C4 (Web Text))

Max Activating Token Index: 693

Text #2

Max Range: 2.0466. Min Range: -2.0466

Max Act: 1.8613. Min Act: -0.0000

Data Index: 1111590 (C4 (Web Text))

Max Activating Token Index: 700

Text #3

Max Range: 2.0466. Min Range: -2.0466

Max Act: 1.9357. Min Act: -0.0000

Data Index: 554364 (C4 (Web Text))

Max Activating Token Index: 714

Text #4

Max Range: 2.0466. Min Range: -2.0466

Max Act: 1.8288. Min Act: -0.0000

Data Index: 986946 (C4 (Web Text))

Max Activating Token Index: 265

Text #5

Max Range: 2.0466. Min Range: -2.0466

Max Act: 1.8195. Min Act: -0.0000

Data Index: 1172570 (C4 (Web Text))

Max Activating Token Index: 710

Text #6

Max Range: 2.0466. Min Range: -2.0466

Max Act: 1.7772. Min Act: -0.0000

Data Index: 960333 (C4 (Web Text))

Max Activating Token Index: 880

Text #7

Max Range: 2.0466. Min Range: -2.0466

Max Act: 1.8653. Min Act: -0.0000

Data Index: 952263 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 2.0466. Min Range: -2.0466

Max Act: 1.7742. Min Act: -0.0000

Data Index: 1066567 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 2.0466. Min Range: -2.0466

Max Act: 1.6928. Min Act: -0.0000

Data Index: 837237 (C4 (Web Text))

Max Activating Token Index: 450

Text #10

Max Range: 2.0466. Min Range: -2.0466

Max Act: 1.5917. Min Act: -0.0000

Data Index: 1144899 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 2.0466. Min Range: -2.0466

Max Act: 1.6887. Min Act: -0.0000

Data Index: 419974 (C4 (Web Text))

Max Activating Token Index: 90

Text #12

Max Range: 2.0466. Min Range: -2.0466

Max Act: 1.4950. Min Act: -0.0000

Data Index: 464217 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 2.0466. Min Range: -2.0466

Max Act: 1.7622. Min Act: -0.0000

Data Index: 917211 (C4 (Web Text))

Max Activating Token Index: 249

Text #14

Max Range: 2.0466. Min Range: -2.0466

Max Act: 1.5730. Min Act: -0.0000

Data Index: 92182 (C4 (Web Text))

Max Activating Token Index: 640

Text #15

Max Range: 2.0466. Min Range: -2.0466

Max Act: 1.5721. Min Act: -0.0000

Data Index: 389260 (C4 (Web Text))

Max Activating Token Index: 417

Text #16

Max Range: 2.0466. Min Range: -2.0466

Max Act: 1.5628. Min Act: -0.0000

Data Index: 783613 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 2.0466. Min Range: -2.0466

Max Act: 1.5633. Min Act: -0.0000

Data Index: 906694 (C4 (Web Text))

Max Activating Token Index: 979

Text #18

Max Range: 2.0466. Min Range: -2.0466

Max Act: 1.6387. Min Act: -0.0000

Data Index: 698901 (C4 (Web Text))

Max Activating Token Index: 400

Text #19

Max Range: 2.0466. Min Range: -2.0466

Max Act: 1.5271. Min Act: -0.0000

Data Index: 1166414 (C4 (Web Text))

Max Activating Token Index: 644