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

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

Neuron 802 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: 3.5876. Min Range: -3.5876

Max Act: 3.5876. Min Act: -0.0000

Data Index: 124514 (C4 (Web Text))

Max Activating Token Index: 609

Text #1

Max Range: 3.5876. Min Range: -3.5876

Max Act: 3.5242. Min Act: -0.0000

Data Index: 842201 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 3.5876. Min Range: -3.5876

Max Act: 3.1176. Min Act: -0.0000

Data Index: 926820 (C4 (Web Text))

Max Activating Token Index: 814

Text #3

Max Range: 3.5876. Min Range: -3.5876

Max Act: 2.9792. Min Act: -0.0000

Data Index: 534712 (C4 (Web Text))

Max Activating Token Index: 813

Text #4

Max Range: 3.5876. Min Range: -3.5876

Max Act: 3.4024. Min Act: -0.0000

Data Index: 269323 (C4 (Web Text))

Max Activating Token Index: 208

Text #5

Max Range: 3.5876. Min Range: -3.5876

Max Act: 3.3558. Min Act: -0.0000

Data Index: 662757 (C4 (Web Text))

Max Activating Token Index: 977

Text #6

Max Range: 3.5876. Min Range: -3.5876

Max Act: 3.3400. Min Act: -0.0000

Data Index: 1084831 (C4 (Web Text))

Max Activating Token Index: 977

Text #7

Max Range: 3.5876. Min Range: -3.5876

Max Act: 3.3264. Min Act: -0.0000

Data Index: 738626 (C4 (Web Text))

Max Activating Token Index: 902

Text #8

Max Range: 3.5876. Min Range: -3.5876

Max Act: 3.1082. Min Act: -0.0000

Data Index: 773045 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 3.5876. Min Range: -3.5876

Max Act: 3.1340. Min Act: -0.0000

Data Index: 450308 (C4 (Web Text))

Max Activating Token Index: 176

Text #10

Max Range: 3.5876. Min Range: -3.5876

Max Act: 3.3863. Min Act: -0.0000

Data Index: 109312 (C4 (Web Text))

Max Activating Token Index: 649

Text #11

Max Range: 3.5876. Min Range: -3.5876

Max Act: 3.5590. Min Act: -0.0000

Data Index: 1223666 (C4 (Web Text))

Max Activating Token Index: 889

Text #12

Max Range: 3.5876. Min Range: -3.5876

Max Act: 3.2293. Min Act: -0.0000

Data Index: 800803 (C4 (Web Text))

Max Activating Token Index: 887

Text #13

Max Range: 3.5876. Min Range: -3.5876

Max Act: 3.2018. Min Act: -0.0000

Data Index: 543233 (C4 (Web Text))

Max Activating Token Index: 800

Text #14

Max Range: 3.5876. Min Range: -3.5876

Max Act: 3.1814. Min Act: -0.0000

Data Index: 404488 (C4 (Web Text))

Max Activating Token Index: 956

Text #15

Max Range: 3.5876. Min Range: -3.5876

Max Act: 3.1437. Min Act: -0.0000

Data Index: 875054 (C4 (Web Text))

Max Activating Token Index: 758

Text #16

Max Range: 3.5876. Min Range: -3.5876

Max Act: 3.1380. Min Act: -0.0000

Data Index: 485824 (C4 (Web Text))

Max Activating Token Index: 581

Text #17

Max Range: 3.5876. Min Range: -3.5876

Max Act: 3.1310. Min Act: -0.0000

Data Index: 121079 (C4 (Web Text))

Max Activating Token Index: 550

Text #18

Max Range: 3.5876. Min Range: -3.5876

Max Act: 2.9443. Min Act: -0.0000

Data Index: 468911 (C4 (Web Text))

Max Activating Token Index: 172

Text #19

Max Range: 3.5876. Min Range: -3.5876

Max Act: 3.0673. Min Act: -0.0000

Data Index: 607047 (C4 (Web Text))

Max Activating Token Index: 913