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

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

Neuron 3584 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: 0.6427. Min Range: -0.6427

Max Act: 0.6414. Min Act: -0.0000

Data Index: 1182261 (C4 (Web Text))

Max Activating Token Index: 223

Text #1

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.6309. Min Act: -0.0000

Data Index: 447238 (C4 (Web Text))

Max Activating Token Index: 946

Text #2

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.6427. Min Act: -0.0000

Data Index: 437999 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.6067. Min Act: -0.0000

Data Index: 737693 (C4 (Web Text))

Max Activating Token Index: 522

Text #4

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.5925. Min Act: -0.0000

Data Index: 909398 (C4 (Web Text))

Max Activating Token Index: 419

Text #5

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.6062. Min Act: -0.0000

Data Index: 306554 (C4 (Web Text))

Max Activating Token Index: 249

Text #6

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.5231. Min Act: -0.0000

Data Index: 978104 (C4 (Web Text))

Max Activating Token Index: 877

Text #7

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.5692. Min Act: -0.0000

Data Index: 636414 (C4 (Web Text))

Max Activating Token Index: 224

Text #8

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.5487. Min Act: -0.0000

Data Index: 1063783 (C4 (Web Text))

Max Activating Token Index: 317

Text #9

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.5450. Min Act: -0.0000

Data Index: 944272 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.5268. Min Act: -0.0000

Data Index: 400746 (C4 (Web Text))

Max Activating Token Index: 828

Text #11

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.5422. Min Act: -0.0000

Data Index: 638676 (C4 (Web Text))

Max Activating Token Index: 463

Text #12

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.5211. Min Act: -0.0000

Data Index: 492559 (C4 (Web Text))

Max Activating Token Index: 875

Text #13

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.5261. Min Act: -0.0000

Data Index: 762583 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.5273. Min Act: -0.0000

Data Index: 1185598 (C4 (Web Text))

Max Activating Token Index: 445

Text #15

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.5373. Min Act: -0.0000

Data Index: 1142718 (C4 (Web Text))

Max Activating Token Index: 327

Text #16

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.4879. Min Act: -0.0000

Data Index: 1247010 (C4 (Web Text))

Max Activating Token Index: 856

Text #17

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.4901. Min Act: -0.0000

Data Index: 42245 (C4 (Web Text))

Max Activating Token Index: 991

Text #18

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.5216. Min Act: -0.0000

Data Index: 1169802 (C4 (Web Text))

Max Activating Token Index: 110

Text #19

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.4998. Min Act: -0.0000

Data Index: 609221 (C4 (Web Text))

Max Activating Token Index: 554