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

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

Neuron 2736 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.9125. Min Act: -0.0001

Data Index: 494679 (C4 (Web Text))

Max Activating Token Index: 398

Text #1

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.8938. Min Act: -0.0001

Data Index: 127721 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.9338. Min Act: -0.0001

Data Index: 881768 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.8914. Min Act: -0.0001

Data Index: 175415 (C4 (Web Text))

Max Activating Token Index: 780

Text #4

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.8624. Min Act: -0.0001

Data Index: 398234 (C4 (Web Text))

Max Activating Token Index: 932

Text #5

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.7842. Min Act: -0.0001

Data Index: 1142154 (C4 (Web Text))

Max Activating Token Index: 450

Text #6

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.8374. Min Act: -0.0001

Data Index: 1083764 (C4 (Web Text))

Max Activating Token Index: 992

Text #7

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.8318. Min Act: -0.0001

Data Index: 356441 (C4 (Web Text))

Max Activating Token Index: 559

Text #8

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.8021. Min Act: -0.0001

Data Index: 652422 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.7643. Min Act: -0.0001

Data Index: 304120 (C4 (Web Text))

Max Activating Token Index: 464

Text #10

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.8366. Min Act: -0.0001

Data Index: 873378 (C4 (Web Text))

Max Activating Token Index: 488

Text #11

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.8328. Min Act: -0.0001

Data Index: 297227 (C4 (Web Text))

Max Activating Token Index: 554

Text #12

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.8063. Min Act: -0.0001

Data Index: 541019 (C4 (Web Text))

Max Activating Token Index: 119

Text #13

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.8645. Min Act: -0.0001

Data Index: 535644 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.8184. Min Act: -0.0001

Data Index: 94070 (C4 (Web Text))

Max Activating Token Index: 977

Text #15

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.8274. Min Act: -0.0001

Data Index: 102473 (C4 (Web Text))

Max Activating Token Index: 556

Text #16

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.7342. Min Act: -0.0001

Data Index: 358621 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.7394. Min Act: -0.0001

Data Index: 902223 (C4 (Web Text))

Max Activating Token Index: 986

Text #18

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.7838. Min Act: -0.0001

Data Index: 582795 (C4 (Web Text))

Max Activating Token Index: 474

Text #19

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.7538. Min Act: -0.0001

Data Index: 1250569 (C4 (Web Text))

Max Activating Token Index: 292