Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2767 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0648. Min Act: -0.0001

Data Index: 33730 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0675. Min Act: -0.0001

Data Index: 610402 (C4 (Web Text))

Max Activating Token Index: 386

Text #2

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0617. Min Act: -0.0001

Data Index: 673131 (C4 (Web Text))

Max Activating Token Index: 868

Text #3

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0600. Min Act: -0.0001

Data Index: 1274134 (C4 (Web Text))

Max Activating Token Index: 1018

Text #4

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0647. Min Act: -0.0001

Data Index: 408587 (C4 (Web Text))

Max Activating Token Index: 577

Text #5

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0573. Min Act: -0.0001

Data Index: 97435 (C4 (Web Text))

Max Activating Token Index: 857

Text #6

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0632. Min Act: -0.0001

Data Index: 31752 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0616. Min Act: -0.0001

Data Index: 175695 (C4 (Web Text))

Max Activating Token Index: 186

Text #8

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0527. Min Act: -0.0001

Data Index: 703736 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0560. Min Act: -0.0001

Data Index: 950160 (C4 (Web Text))

Max Activating Token Index: 548

Text #10

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0527. Min Act: -0.0001

Data Index: 733378 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0498. Min Act: -0.0001

Data Index: 1293488 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0510. Min Act: -0.0001

Data Index: 952227 (C4 (Web Text))

Max Activating Token Index: 479

Text #13

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0507. Min Act: -0.0001

Data Index: 709487 (C4 (Web Text))

Max Activating Token Index: 502

Text #14

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0521. Min Act: -0.0001

Data Index: 713160 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0442. Min Act: -0.0001

Data Index: 5557 (C4 (Web Text))

Max Activating Token Index: 525

Text #16

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0491. Min Act: -0.0001

Data Index: 392134 (C4 (Web Text))

Max Activating Token Index: 969

Text #17

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0451. Min Act: -0.0001

Data Index: 1289407 (C4 (Web Text))

Max Activating Token Index: 943

Text #18

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0474. Min Act: -0.0001

Data Index: 94960 (C4 (Web Text))

Max Activating Token Index: 403

Text #19

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0492. Min Act: -0.0001

Data Index: 465921 (C4 (Web Text))

Max Activating Token Index: 958