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

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

Neuron 5079 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: 0.6857. Min Range: -0.6857

Max Act: 0.6857. Min Act: -0.0000

Data Index: 912766 (C4 (Web Text))

Max Activating Token Index: 419

Text #1

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.6133. Min Act: -0.0000

Data Index: 561742 (C4 (Web Text))

Max Activating Token Index: 230

Text #2

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.5941. Min Act: -0.0000

Data Index: 883027 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.5716. Min Act: -0.0000

Data Index: 432670 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.5545. Min Act: -0.0000

Data Index: 455604 (C4 (Web Text))

Max Activating Token Index: 231

Text #5

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.5440. Min Act: -0.0000

Data Index: 110443 (C4 (Web Text))

Max Activating Token Index: 740

Text #6

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.6063. Min Act: 0.0000

Data Index: 125298 (C4 (Web Text))

Max Activating Token Index: 627

Text #7

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.5440. Min Act: -0.0000

Data Index: 961708 (C4 (Web Text))

Max Activating Token Index: 735

Text #8

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.5387. Min Act: -0.0000

Data Index: 831130 (C4 (Web Text))

Max Activating Token Index: 612

Text #9

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.5385. Min Act: -0.0000

Data Index: 1273460 (C4 (Web Text))

Max Activating Token Index: 916

Text #10

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.5450. Min Act: -0.0000

Data Index: 283496 (C4 (Web Text))

Max Activating Token Index: 656

Text #11

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.4838. Min Act: -0.0000

Data Index: 51263 (C4 (Web Text))

Max Activating Token Index: 243

Text #12

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.4933. Min Act: -0.0000

Data Index: 288489 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.4665. Min Act: -0.0000

Data Index: 826800 (C4 (Web Text))

Max Activating Token Index: 889

Text #14

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.4630. Min Act: -0.0000

Data Index: 15172 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.4741. Min Act: -0.0000

Data Index: 1150183 (C4 (Web Text))

Max Activating Token Index: 41

Text #16

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.4663. Min Act: -0.0000

Data Index: 601691 (C4 (Web Text))

Max Activating Token Index: 875

Text #17

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.4682. Min Act: -0.0000

Data Index: 922523 (C4 (Web Text))

Max Activating Token Index: 1006

Text #18

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.4633. Min Act: -0.0000

Data Index: 20082 (C4 (Web Text))

Max Activating Token Index: 208

Text #19

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.4315. Min Act: -0.0000

Data Index: 569430 (C4 (Web Text))

Max Activating Token Index: 972