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

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

Neuron 4070 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7619. Min Range: -3.7619

Max Act: 3.7619. Min Act: -0.0000

Data Index: 835656 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 3.7619. Min Range: -3.7619

Max Act: 2.9997. Min Act: -0.0000

Data Index: 1130828 (C4 (Web Text))

Max Activating Token Index: 511

Text #2

Max Range: 3.7619. Min Range: -3.7619

Max Act: 2.7240. Min Act: -0.0000

Data Index: 967767 (C4 (Web Text))

Max Activating Token Index: 986

Text #3

Max Range: 3.7619. Min Range: -3.7619

Max Act: 2.9823. Min Act: -0.0000

Data Index: 968993 (C4 (Web Text))

Max Activating Token Index: 948

Text #4

Max Range: 3.7619. Min Range: -3.7619

Max Act: 2.7978. Min Act: -0.0000

Data Index: 648002 (C4 (Web Text))

Max Activating Token Index: 1019

Text #5

Max Range: 3.7619. Min Range: -3.7619

Max Act: 2.7830. Min Act: -0.0000

Data Index: 635670 (C4 (Web Text))

Max Activating Token Index: 956

Text #6

Max Range: 3.7619. Min Range: -3.7619

Max Act: 2.7594. Min Act: -0.0000

Data Index: 1078552 (C4 (Web Text))

Max Activating Token Index: 725

Text #7

Max Range: 3.7619. Min Range: -3.7619

Max Act: 2.7763. Min Act: -0.0000

Data Index: 10000 (C4 (Web Text))

Max Activating Token Index: 644

Text #8

Max Range: 3.7619. Min Range: -3.7619

Max Act: 2.6631. Min Act: -0.0000

Data Index: 1282893 (C4 (Web Text))

Max Activating Token Index: 529

Text #9

Max Range: 3.7619. Min Range: -3.7619

Max Act: 2.5216. Min Act: -0.0000

Data Index: 1222532 (C4 (Web Text))

Max Activating Token Index: 543

Text #10

Max Range: 3.7619. Min Range: -3.7619

Max Act: 2.7726. Min Act: -0.0000

Data Index: 566191 (C4 (Web Text))

Max Activating Token Index: 364

Text #11

Max Range: 3.7619. Min Range: -3.7619

Max Act: 2.6462. Min Act: -0.0000

Data Index: 678596 (C4 (Web Text))

Max Activating Token Index: 764

Text #12

Max Range: 3.7619. Min Range: -3.7619

Max Act: 2.4901. Min Act: -0.0000

Data Index: 695721 (C4 (Web Text))

Max Activating Token Index: 936

Text #13

Max Range: 3.7619. Min Range: -3.7619

Max Act: 2.5746. Min Act: -0.0000

Data Index: 558622 (C4 (Web Text))

Max Activating Token Index: 213

Text #14

Max Range: 3.7619. Min Range: -3.7619

Max Act: 2.4205. Min Act: -0.0000

Data Index: 786813 (C4 (Web Text))

Max Activating Token Index: 551

Text #15

Max Range: 3.7619. Min Range: -3.7619

Max Act: 2.3670. Min Act: -0.0000

Data Index: 1031603 (C4 (Web Text))

Max Activating Token Index: 634

Text #16

Max Range: 3.7619. Min Range: -3.7619

Max Act: 2.3573. Min Act: -0.0000

Data Index: 218880 (C4 (Web Text))

Max Activating Token Index: 421

Text #17

Max Range: 3.7619. Min Range: -3.7619

Max Act: 2.3465. Min Act: -0.0000

Data Index: 666988 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 3.7619. Min Range: -3.7619

Max Act: 2.2200. Min Act: -0.0000

Data Index: 982587 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 3.7619. Min Range: -3.7619

Max Act: 2.3260. Min Act: -0.0000

Data Index: 865118 (C4 (Web Text))

Max Activating Token Index: 164