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

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

Neuron 2822 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0108. Min Act: -0.0003

Data Index: 793752 (C4 (Web Text))

Max Activating Token Index: 656

Text #1

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0096. Min Act: -0.0003

Data Index: 333189 (C4 (Web Text))

Max Activating Token Index: 462

Text #2

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0098. Min Act: -0.0004

Data Index: 488016 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0093. Min Act: -0.0003

Data Index: 962372 (C4 (Web Text))

Max Activating Token Index: 807

Text #4

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0089. Min Act: -0.0003

Data Index: 625659 (C4 (Web Text))

Max Activating Token Index: 623

Text #5

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0091. Min Act: -0.0003

Data Index: 272621 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0092. Min Act: -0.0003

Data Index: 502319 (C4 (Web Text))

Max Activating Token Index: 714

Text #7

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0092. Min Act: -0.0003

Data Index: 290057 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0089. Min Act: -0.0003

Data Index: 656200 (C4 (Web Text))

Max Activating Token Index: 807

Text #9

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0090. Min Act: -0.0003

Data Index: 313103 (C4 (Web Text))

Max Activating Token Index: 651

Text #10

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0078. Min Act: -0.0003

Data Index: 302002 (C4 (Web Text))

Max Activating Token Index: 563

Text #11

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0088. Min Act: -0.0003

Data Index: 118038 (C4 (Web Text))

Max Activating Token Index: 437

Text #12

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0082. Min Act: -0.0003

Data Index: 763359 (C4 (Web Text))

Max Activating Token Index: 687

Text #13

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0081. Min Act: -0.0003

Data Index: 1044510 (C4 (Web Text))

Max Activating Token Index: 540

Text #14

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0082. Min Act: -0.0003

Data Index: 398737 (C4 (Web Text))

Max Activating Token Index: 605

Text #15

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0103. Min Act: -0.0003

Data Index: 213105 (C4 (Web Text))

Max Activating Token Index: 765

Text #16

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0085. Min Act: -0.0003

Data Index: 357120 (C4 (Web Text))

Max Activating Token Index: 775

Text #17

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0083. Min Act: -0.0003

Data Index: 959636 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0090. Min Act: -0.0003

Data Index: 326232 (C4 (Web Text))

Max Activating Token Index: 641

Text #19

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0076. Min Act: -0.0003

Data Index: 1251964 (C4 (Web Text))

Max Activating Token Index: 766