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

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

Neuron 846 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.4089. Min Act: -0.0001

Data Index: 666875 (C4 (Web Text))

Max Activating Token Index: 574

Text #1

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3672. Min Act: -0.0001

Data Index: 912567 (C4 (Web Text))

Max Activating Token Index: 843

Text #2

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3516. Min Act: -0.0001

Data Index: 761374 (C4 (Web Text))

Max Activating Token Index: 637

Text #3

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3677. Min Act: -0.0001

Data Index: 509155 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2886. Min Act: -0.0001

Data Index: 1283996 (C4 (Web Text))

Max Activating Token Index: 980

Text #5

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2757. Min Act: -0.0001

Data Index: 678106 (C4 (Web Text))

Max Activating Token Index: 889

Text #6

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3013. Min Act: -0.0000

Data Index: 650203 (C4 (Web Text))

Max Activating Token Index: 547

Text #7

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2773. Min Act: -0.0001

Data Index: 276943 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2766. Min Act: -0.0001

Data Index: 33368 (C4 (Web Text))

Max Activating Token Index: 815

Text #9

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2774. Min Act: -0.0001

Data Index: 4713 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2667. Min Act: -0.0000

Data Index: 1112724 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2734. Min Act: -0.0001

Data Index: 274146 (C4 (Web Text))

Max Activating Token Index: 858

Text #12

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2355. Min Act: -0.0000

Data Index: 41773 (C4 (Web Text))

Max Activating Token Index: 598

Text #13

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2684. Min Act: -0.0001

Data Index: 1033842 (C4 (Web Text))

Max Activating Token Index: 881

Text #14

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2517. Min Act: -0.0001

Data Index: 119072 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2512. Min Act: -0.0001

Data Index: 138192 (C4 (Web Text))

Max Activating Token Index: 439

Text #16

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2334. Min Act: -0.0000

Data Index: 892743 (C4 (Web Text))

Max Activating Token Index: 810

Text #17

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2472. Min Act: -0.0000

Data Index: 294040 (C4 (Web Text))

Max Activating Token Index: 1005

Text #18

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2591. Min Act: -0.0001

Data Index: 543416 (C4 (Web Text))

Max Activating Token Index: 823

Text #19

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2590. Min Act: -0.0001

Data Index: 138795 (C4 (Web Text))

Max Activating Token Index: 710