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

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

Neuron 3420 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.7753. Min Act: -0.0000

Data Index: 217675 (C4 (Web Text))

Max Activating Token Index: 939

Text #1

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.7363. Min Act: -0.0000

Data Index: 641192 (C4 (Web Text))

Max Activating Token Index: 491

Text #2

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.6652. Min Act: -0.0001

Data Index: 790108 (C4 (Web Text))

Max Activating Token Index: 908

Text #3

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.7015. Min Act: -0.0000

Data Index: 1019794 (C4 (Web Text))

Max Activating Token Index: 678

Text #4

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.6360. Min Act: -0.0000

Data Index: 1000872 (C4 (Web Text))

Max Activating Token Index: 850

Text #5

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.6449. Min Act: -0.0000

Data Index: 258222 (C4 (Web Text))

Max Activating Token Index: 853

Text #6

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.6281. Min Act: -0.0000

Data Index: 22506 (C4 (Web Text))

Max Activating Token Index: 917

Text #7

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.6317. Min Act: -0.0000

Data Index: 957217 (C4 (Web Text))

Max Activating Token Index: 768

Text #8

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.5867. Min Act: -0.0000

Data Index: 742933 (C4 (Web Text))

Max Activating Token Index: 309

Text #9

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.5444. Min Act: -0.0001

Data Index: 98657 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.5633. Min Act: -0.0000

Data Index: 547939 (C4 (Web Text))

Max Activating Token Index: 670

Text #11

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.5792. Min Act: -0.0000

Data Index: 724582 (C4 (Web Text))

Max Activating Token Index: 798

Text #12

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.5804. Min Act: -0.0001

Data Index: 489804 (C4 (Web Text))

Max Activating Token Index: 840

Text #13

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.5935. Min Act: -0.0000

Data Index: 1334952 (C4 (Web Text))

Max Activating Token Index: 625

Text #14

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.5968. Min Act: -0.0000

Data Index: 472476 (C4 (Web Text))

Max Activating Token Index: 655

Text #15

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.5609. Min Act: -0.0000

Data Index: 319987 (C4 (Web Text))

Max Activating Token Index: 236

Text #16

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.5395. Min Act: -0.0000

Data Index: 269704 (C4 (Web Text))

Max Activating Token Index: 931

Text #17

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.5232. Min Act: -0.0000

Data Index: 468506 (C4 (Web Text))

Max Activating Token Index: 990

Text #18

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.5547. Min Act: -0.0000

Data Index: 445415 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.5536. Min Act: -0.0001

Data Index: 1193489 (C4 (Web Text))

Max Activating Token Index: 706