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

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

Neuron 3016 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: 2.8765. Min Range: -2.8765

Max Act: 2.8765. Min Act: -0.0000

Data Index: 362383 (C4 (Web Text))

Max Activating Token Index: 462

Text #1

Max Range: 2.8765. Min Range: -2.8765

Max Act: 2.7043. Min Act: -0.0000

Data Index: 506943 (C4 (Web Text))

Max Activating Token Index: 524

Text #2

Max Range: 2.8765. Min Range: -2.8765

Max Act: 2.3996. Min Act: -0.0000

Data Index: 450752 (C4 (Web Text))

Max Activating Token Index: 823

Text #3

Max Range: 2.8765. Min Range: -2.8765

Max Act: 2.4797. Min Act: -0.0000

Data Index: 158655 (C4 (Web Text))

Max Activating Token Index: 1020

Text #4

Max Range: 2.8765. Min Range: -2.8765

Max Act: 2.4571. Min Act: -0.0000

Data Index: 823316 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 2.8765. Min Range: -2.8765

Max Act: 2.2488. Min Act: -0.0000

Data Index: 89089 (C4 (Web Text))

Max Activating Token Index: 236

Text #6

Max Range: 2.8765. Min Range: -2.8765

Max Act: 2.2966. Min Act: -0.0000

Data Index: 654841 (C4 (Web Text))

Max Activating Token Index: 601

Text #7

Max Range: 2.8765. Min Range: -2.8765

Max Act: 2.2449. Min Act: -0.0000

Data Index: 584500 (C4 (Web Text))

Max Activating Token Index: 525

Text #8

Max Range: 2.8765. Min Range: -2.8765

Max Act: 2.0786. Min Act: -0.0000

Data Index: 395107 (C4 (Web Text))

Max Activating Token Index: 961

Text #9

Max Range: 2.8765. Min Range: -2.8765

Max Act: 2.0635. Min Act: -0.0000

Data Index: 243465 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 2.8765. Min Range: -2.8765

Max Act: 2.0636. Min Act: -0.0000

Data Index: 1133242 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 2.8765. Min Range: -2.8765

Max Act: 2.0243. Min Act: -0.0000

Data Index: 167511 (C4 (Web Text))

Max Activating Token Index: 761

Text #12

Max Range: 2.8765. Min Range: -2.8765

Max Act: 1.9670. Min Act: -0.0000

Data Index: 826333 (C4 (Web Text))

Max Activating Token Index: 494

Text #13

Max Range: 2.8765. Min Range: -2.8765

Max Act: 1.9447. Min Act: -0.0000

Data Index: 935941 (C4 (Web Text))

Max Activating Token Index: 397

Text #14

Max Range: 2.8765. Min Range: -2.8765

Max Act: 2.0440. Min Act: -0.0000

Data Index: 153295 (C4 (Web Text))

Max Activating Token Index: 373

Text #15

Max Range: 2.8765. Min Range: -2.8765

Max Act: 2.0175. Min Act: -0.0000

Data Index: 1114215 (C4 (Web Text))

Max Activating Token Index: 859

Text #16

Max Range: 2.8765. Min Range: -2.8765

Max Act: 1.7804. Min Act: -0.0000

Data Index: 414606 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 2.8765. Min Range: -2.8765

Max Act: 1.9888. Min Act: -0.0000

Data Index: 649605 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 2.8765. Min Range: -2.8765

Max Act: 1.8941. Min Act: -0.0000

Data Index: 1334678 (C4 (Web Text))

Max Activating Token Index: 615

Text #19

Max Range: 2.8765. Min Range: -2.8765

Max Act: 1.8774. Min Act: -0.0000

Data Index: 753168 (C4 (Web Text))

Max Activating Token Index: 390