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

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

Neuron 3217 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2257. Min Range: -1.2257

Max Act: 1.2257. Min Act: -0.0000

Data Index: 391435 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 1.2257. Min Range: -1.2257

Max Act: 1.2025. Min Act: -0.0000

Data Index: 233550 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 1.2257. Min Range: -1.2257

Max Act: 1.0450. Min Act: -0.0000

Data Index: 754277 (C4 (Web Text))

Max Activating Token Index: 508

Text #3

Max Range: 1.2257. Min Range: -1.2257

Max Act: 0.9756. Min Act: -0.0000

Data Index: 762401 (C4 (Web Text))

Max Activating Token Index: 879

Text #4

Max Range: 1.2257. Min Range: -1.2257

Max Act: 1.0987. Min Act: -0.0000

Data Index: 806980 (C4 (Web Text))

Max Activating Token Index: 703

Text #5

Max Range: 1.2257. Min Range: -1.2257

Max Act: 1.0248. Min Act: -0.0000

Data Index: 1163755 (C4 (Web Text))

Max Activating Token Index: 1020

Text #6

Max Range: 1.2257. Min Range: -1.2257

Max Act: 1.0537. Min Act: -0.0000

Data Index: 953570 (C4 (Web Text))

Max Activating Token Index: 685

Text #7

Max Range: 1.2257. Min Range: -1.2257

Max Act: 1.0174. Min Act: -0.0000

Data Index: 102379 (C4 (Web Text))

Max Activating Token Index: 558

Text #8

Max Range: 1.2257. Min Range: -1.2257

Max Act: 0.9841. Min Act: -0.0000

Data Index: 1595939 (Python Code)

Max Activating Token Index: 565

Text #9

Max Range: 1.2257. Min Range: -1.2257

Max Act: 0.9475. Min Act: -0.0000

Data Index: 1012603 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 1.2257. Min Range: -1.2257

Max Act: 0.9293. Min Act: -0.0000

Data Index: 158914 (C4 (Web Text))

Max Activating Token Index: 633

Text #11

Max Range: 1.2257. Min Range: -1.2257

Max Act: 0.8815. Min Act: -0.0000

Data Index: 399523 (C4 (Web Text))

Max Activating Token Index: 506

Text #12

Max Range: 1.2257. Min Range: -1.2257

Max Act: 0.8708. Min Act: -0.0000

Data Index: 986216 (C4 (Web Text))

Max Activating Token Index: 349

Text #13

Max Range: 1.2257. Min Range: -1.2257

Max Act: 0.8827. Min Act: -0.0000

Data Index: 444364 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 1.2257. Min Range: -1.2257

Max Act: 0.8540. Min Act: -0.0000

Data Index: 1281101 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 1.2257. Min Range: -1.2257

Max Act: 0.8292. Min Act: -0.0000

Data Index: 981790 (C4 (Web Text))

Max Activating Token Index: 800

Text #16

Max Range: 1.2257. Min Range: -1.2257

Max Act: 0.8759. Min Act: -0.0000

Data Index: 1281295 (C4 (Web Text))

Max Activating Token Index: 481

Text #17

Max Range: 1.2257. Min Range: -1.2257

Max Act: 0.8513. Min Act: -0.0000

Data Index: 160235 (C4 (Web Text))

Max Activating Token Index: 676

Text #18

Max Range: 1.2257. Min Range: -1.2257

Max Act: 0.8281. Min Act: -0.0000

Data Index: 400560 (C4 (Web Text))

Max Activating Token Index: 175

Text #19

Max Range: 1.2257. Min Range: -1.2257

Max Act: 0.8041. Min Act: -0.0000

Data Index: 909334 (C4 (Web Text))

Max Activating Token Index: 635