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

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

Neuron 3408 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.4975. Min Act: -0.0001

Data Index: 1166357 (C4 (Web Text))

Max Activating Token Index: 732

Text #1

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.4473. Min Act: -0.0001

Data Index: 881022 (C4 (Web Text))

Max Activating Token Index: 601

Text #2

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.4553. Min Act: -0.0001

Data Index: 495402 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.4540. Min Act: -0.0001

Data Index: 211777 (C4 (Web Text))

Max Activating Token Index: 977

Text #4

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.4153. Min Act: -0.0001

Data Index: 200020 (C4 (Web Text))

Max Activating Token Index: 204

Text #5

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3930. Min Act: -0.0001

Data Index: 717425 (C4 (Web Text))

Max Activating Token Index: 914

Text #6

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3847. Min Act: -0.0001

Data Index: 674110 (C4 (Web Text))

Max Activating Token Index: 487

Text #7

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3768. Min Act: -0.0001

Data Index: 355230 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3860. Min Act: -0.0001

Data Index: 684221 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3913. Min Act: -0.0001

Data Index: 1124256 (C4 (Web Text))

Max Activating Token Index: 549

Text #10

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3824. Min Act: -0.0001

Data Index: 414502 (C4 (Web Text))

Max Activating Token Index: 778

Text #11

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3781. Min Act: -0.0001

Data Index: 847771 (C4 (Web Text))

Max Activating Token Index: 344

Text #12

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3787. Min Act: -0.0001

Data Index: 844122 (C4 (Web Text))

Max Activating Token Index: 477

Text #13

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3614. Min Act: -0.0001

Data Index: 538537 (C4 (Web Text))

Max Activating Token Index: 623

Text #14

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3751. Min Act: -0.0001

Data Index: 209112 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3748. Min Act: -0.0001

Data Index: 799287 (C4 (Web Text))

Max Activating Token Index: 824

Text #16

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3720. Min Act: -0.0001

Data Index: 793425 (C4 (Web Text))

Max Activating Token Index: 902

Text #17

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3799. Min Act: -0.0001

Data Index: 1043996 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3541. Min Act: -0.0001

Data Index: 692758 (C4 (Web Text))

Max Activating Token Index: 814

Text #19

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3545. Min Act: -0.0001

Data Index: 1007422 (C4 (Web Text))

Max Activating Token Index: 553