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

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

Neuron 687 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: 1.5331. Min Range: -1.5331

Max Act: 1.5331. Min Act: -0.0000

Data Index: 1275385 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 1.5331. Min Range: -1.5331

Max Act: 1.2272. Min Act: -0.0000

Data Index: 61618 (C4 (Web Text))

Max Activating Token Index: 185

Text #2

Max Range: 1.5331. Min Range: -1.5331

Max Act: 1.1779. Min Act: -0.0000

Data Index: 169767 (C4 (Web Text))

Max Activating Token Index: 752

Text #3

Max Range: 1.5331. Min Range: -1.5331

Max Act: 1.0965. Min Act: 0.0000

Data Index: 486616 (C4 (Web Text))

Max Activating Token Index: 596

Text #4

Max Range: 1.5331. Min Range: -1.5331

Max Act: 1.1537. Min Act: -0.0000

Data Index: 803712 (C4 (Web Text))

Max Activating Token Index: 660

Text #5

Max Range: 1.5331. Min Range: -1.5331

Max Act: 1.0776. Min Act: -0.0000

Data Index: 1069781 (C4 (Web Text))

Max Activating Token Index: 967

Text #6

Max Range: 1.5331. Min Range: -1.5331

Max Act: 1.0433. Min Act: -0.0000

Data Index: 539261 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 1.5331. Min Range: -1.5331

Max Act: 1.0303. Min Act: -0.0000

Data Index: 1012418 (C4 (Web Text))

Max Activating Token Index: 705

Text #8

Max Range: 1.5331. Min Range: -1.5331

Max Act: 1.0105. Min Act: 0.0000

Data Index: 1002073 (C4 (Web Text))

Max Activating Token Index: 783

Text #9

Max Range: 1.5331. Min Range: -1.5331

Max Act: 0.9997. Min Act: 0.0001

Data Index: 362415 (C4 (Web Text))

Max Activating Token Index: 682

Text #10

Max Range: 1.5331. Min Range: -1.5331

Max Act: 1.0042. Min Act: 0.0000

Data Index: 905645 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 1.5331. Min Range: -1.5331

Max Act: 1.0197. Min Act: -0.0000

Data Index: 804505 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 1.5331. Min Range: -1.5331

Max Act: 0.9585. Min Act: 0.0001

Data Index: 293470 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 1.5331. Min Range: -1.5331

Max Act: 1.0143. Min Act: -0.0000

Data Index: 280252 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 1.5331. Min Range: -1.5331

Max Act: 0.9786. Min Act: -0.0000

Data Index: 877370 (C4 (Web Text))

Max Activating Token Index: 886

Text #15

Max Range: 1.5331. Min Range: -1.5331

Max Act: 0.9403. Min Act: -0.0000

Data Index: 1303308 (C4 (Web Text))

Max Activating Token Index: 67

Text #16

Max Range: 1.5331. Min Range: -1.5331

Max Act: 0.9771. Min Act: 0.0000

Data Index: 794890 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 1.5331. Min Range: -1.5331

Max Act: 0.9769. Min Act: -0.0000

Data Index: 763431 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 1.5331. Min Range: -1.5331

Max Act: 1.0276. Min Act: 0.0001

Data Index: 1320025 (C4 (Web Text))

Max Activating Token Index: 337

Text #19

Max Range: 1.5331. Min Range: -1.5331

Max Act: 0.9397. Min Act: -0.0000

Data Index: 1083089 (C4 (Web Text))

Max Activating Token Index: 90