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

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

Neuron 1069 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: 1.6440. Min Range: -1.6440

Max Act: 1.6440. Min Act: -0.0000

Data Index: 764027 (C4 (Web Text))

Max Activating Token Index: 335

Text #1

Max Range: 1.6440. Min Range: -1.6440

Max Act: 0.9443. Min Act: -0.0000

Data Index: 1110696 (C4 (Web Text))

Max Activating Token Index: 265

Text #2

Max Range: 1.6440. Min Range: -1.6440

Max Act: 1.0425. Min Act: -0.0000

Data Index: 1063436 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 1.6440. Min Range: -1.6440

Max Act: 1.0568. Min Act: -0.0000

Data Index: 777236 (C4 (Web Text))

Max Activating Token Index: 335

Text #4

Max Range: 1.6440. Min Range: -1.6440

Max Act: 0.9771. Min Act: -0.0000

Data Index: 332209 (C4 (Web Text))

Max Activating Token Index: 573

Text #5

Max Range: 1.6440. Min Range: -1.6440

Max Act: 0.9476. Min Act: -0.0000

Data Index: 1008917 (C4 (Web Text))

Max Activating Token Index: 992

Text #6

Max Range: 1.6440. Min Range: -1.6440

Max Act: 1.0079. Min Act: -0.0000

Data Index: 24044 (C4 (Web Text))

Max Activating Token Index: 458

Text #7

Max Range: 1.6440. Min Range: -1.6440

Max Act: 0.9776. Min Act: -0.0000

Data Index: 690366 (C4 (Web Text))

Max Activating Token Index: 615

Text #8

Max Range: 1.6440. Min Range: -1.6440

Max Act: 0.9485. Min Act: -0.0000

Data Index: 1487097 (Python Code)

Max Activating Token Index: 613

Text #9

Max Range: 1.6440. Min Range: -1.6440

Max Act: 0.9069. Min Act: -0.0000

Data Index: 220136 (C4 (Web Text))

Max Activating Token Index: 608

Text #10

Max Range: 1.6440. Min Range: -1.6440

Max Act: 0.9385. Min Act: -0.0000

Data Index: 613498 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 1.6440. Min Range: -1.6440

Max Act: 0.9241. Min Act: 0.0000

Data Index: 1408227 (Python Code)

Max Activating Token Index: 171

Text #12

Max Range: 1.6440. Min Range: -1.6440

Max Act: 0.8611. Min Act: -0.0000

Data Index: 760953 (C4 (Web Text))

Max Activating Token Index: 531

Text #13

Max Range: 1.6440. Min Range: -1.6440

Max Act: 0.8423. Min Act: -0.0000

Data Index: 1126301 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 1.6440. Min Range: -1.6440

Max Act: 0.8398. Min Act: -0.0000

Data Index: 603620 (C4 (Web Text))

Max Activating Token Index: 321

Text #15

Max Range: 1.6440. Min Range: -1.6440

Max Act: 0.8292. Min Act: -0.0000

Data Index: 412096 (C4 (Web Text))

Max Activating Token Index: 368

Text #16

Max Range: 1.6440. Min Range: -1.6440

Max Act: 0.8261. Min Act: -0.0000

Data Index: 1647872 (Python Code)

Max Activating Token Index: 764

Text #17

Max Range: 1.6440. Min Range: -1.6440

Max Act: 0.8006. Min Act: -0.0000

Data Index: 798965 (C4 (Web Text))

Max Activating Token Index: 335

Text #18

Max Range: 1.6440. Min Range: -1.6440

Max Act: 0.8226. Min Act: -0.0000

Data Index: 691689 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 1.6440. Min Range: -1.6440

Max Act: 0.8915. Min Act: -0.0000

Data Index: 836136 (C4 (Web Text))

Max Activating Token Index: 910