Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4841 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7079. Min Range: -0.7079

Max Act: 0.7079. Min Act: -0.0000

Data Index: 91019 (C4 (Web Text))

Max Activating Token Index: 317

Text #1

Max Range: 0.7079. Min Range: -0.7079

Max Act: 0.6631. Min Act: -0.0000

Data Index: 534928 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 0.7079. Min Range: -0.7079

Max Act: 0.6950. Min Act: -0.0000

Data Index: 310351 (C4 (Web Text))

Max Activating Token Index: 553

Text #3

Max Range: 0.7079. Min Range: -0.7079

Max Act: 0.6243. Min Act: -0.0000

Data Index: 1157479 (C4 (Web Text))

Max Activating Token Index: 672

Text #4

Max Range: 0.7079. Min Range: -0.7079

Max Act: 0.5823. Min Act: -0.0000

Data Index: 1133498 (C4 (Web Text))

Max Activating Token Index: 450

Text #5

Max Range: 0.7079. Min Range: -0.7079

Max Act: 0.5985. Min Act: -0.0000

Data Index: 585230 (C4 (Web Text))

Max Activating Token Index: 442

Text #6

Max Range: 0.7079. Min Range: -0.7079

Max Act: 0.5945. Min Act: -0.0000

Data Index: 588420 (C4 (Web Text))

Max Activating Token Index: 436

Text #7

Max Range: 0.7079. Min Range: -0.7079

Max Act: 0.5691. Min Act: -0.0000

Data Index: 1090004 (C4 (Web Text))

Max Activating Token Index: 426

Text #8

Max Range: 0.7079. Min Range: -0.7079

Max Act: 0.5462. Min Act: -0.0000

Data Index: 818674 (C4 (Web Text))

Max Activating Token Index: 978

Text #9

Max Range: 0.7079. Min Range: -0.7079

Max Act: 0.5840. Min Act: -0.0000

Data Index: 454773 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 0.7079. Min Range: -0.7079

Max Act: 0.5762. Min Act: -0.0000

Data Index: 922347 (C4 (Web Text))

Max Activating Token Index: 795

Text #11

Max Range: 0.7079. Min Range: -0.7079

Max Act: 0.5371. Min Act: -0.0000

Data Index: 1065360 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 0.7079. Min Range: -0.7079

Max Act: 0.5274. Min Act: -0.0000

Data Index: 1522961 (Python Code)

Max Activating Token Index: 798

Text #13

Max Range: 0.7079. Min Range: -0.7079

Max Act: 0.5618. Min Act: -0.0000

Data Index: 122433 (C4 (Web Text))

Max Activating Token Index: 236

Text #14

Max Range: 0.7079. Min Range: -0.7079

Max Act: 0.5364. Min Act: -0.0000

Data Index: 739508 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 0.7079. Min Range: -0.7079

Max Act: 0.5258. Min Act: -0.0000

Data Index: 911060 (C4 (Web Text))

Max Activating Token Index: 380

Text #16

Max Range: 0.7079. Min Range: -0.7079

Max Act: 0.5284. Min Act: -0.0000

Data Index: 627462 (C4 (Web Text))

Max Activating Token Index: 834

Text #17

Max Range: 0.7079. Min Range: -0.7079

Max Act: 0.5252. Min Act: -0.0000

Data Index: 210987 (C4 (Web Text))

Max Activating Token Index: 488

Text #18

Max Range: 0.7079. Min Range: -0.7079

Max Act: 0.5206. Min Act: -0.0000

Data Index: 385443 (C4 (Web Text))

Max Activating Token Index: 836

Text #19

Max Range: 0.7079. Min Range: -0.7079

Max Act: 0.5262. Min Act: -0.0000

Data Index: 587972 (C4 (Web Text))

Max Activating Token Index: 708