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

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

Neuron 1635 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.7680. Min Act: -0.0000

Data Index: 1150498 (C4 (Web Text))

Max Activating Token Index: 753

Text #1

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.6355. Min Act: -0.0000

Data Index: 659717 (C4 (Web Text))

Max Activating Token Index: 918

Text #2

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.6380. Min Act: -0.0000

Data Index: 1326878 (C4 (Web Text))

Max Activating Token Index: 202

Text #3

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.5855. Min Act: -0.0000

Data Index: 387562 (C4 (Web Text))

Max Activating Token Index: 242

Text #4

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.5942. Min Act: -0.0000

Data Index: 535548 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.5569. Min Act: -0.0000

Data Index: 609726 (C4 (Web Text))

Max Activating Token Index: 982

Text #6

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.5584. Min Act: -0.0000

Data Index: 773101 (C4 (Web Text))

Max Activating Token Index: 807

Text #7

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.5419. Min Act: -0.0000

Data Index: 142557 (C4 (Web Text))

Max Activating Token Index: 724

Text #8

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.5867. Min Act: -0.0000

Data Index: 5194 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.5642. Min Act: -0.0000

Data Index: 260510 (C4 (Web Text))

Max Activating Token Index: 986

Text #10

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.5578. Min Act: 0.0000

Data Index: 712029 (C4 (Web Text))

Max Activating Token Index: 633

Text #11

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.5577. Min Act: -0.0000

Data Index: 174327 (C4 (Web Text))

Max Activating Token Index: 831

Text #12

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.5579. Min Act: -0.0000

Data Index: 549327 (C4 (Web Text))

Max Activating Token Index: 972

Text #13

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.5295. Min Act: -0.0000

Data Index: 1076685 (C4 (Web Text))

Max Activating Token Index: 937

Text #14

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.5572. Min Act: -0.0000

Data Index: 18151 (C4 (Web Text))

Max Activating Token Index: 644

Text #15

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.5340. Min Act: -0.0000

Data Index: 317165 (C4 (Web Text))

Max Activating Token Index: 899

Text #16

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.5496. Min Act: -0.0000

Data Index: 856170 (C4 (Web Text))

Max Activating Token Index: 567

Text #17

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.5423. Min Act: 0.0000

Data Index: 129386 (C4 (Web Text))

Max Activating Token Index: 534

Text #18

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.5163. Min Act: -0.0000

Data Index: 705771 (C4 (Web Text))

Max Activating Token Index: 519

Text #19

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.5127. Min Act: 0.0000

Data Index: 604805 (C4 (Web Text))

Max Activating Token Index: 344