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

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

Neuron 2842 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.8869. Min Act: -0.0001

Data Index: 1154263 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.7845. Min Act: -0.0001

Data Index: 774595 (C4 (Web Text))

Max Activating Token Index: 800

Text #2

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.6864. Min Act: -0.0000

Data Index: 50421 (C4 (Web Text))

Max Activating Token Index: 991

Text #3

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.6648. Min Act: -0.0001

Data Index: 922022 (C4 (Web Text))

Max Activating Token Index: 393

Text #4

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.6124. Min Act: -0.0000

Data Index: 1307430 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.6314. Min Act: -0.0001

Data Index: 129256 (C4 (Web Text))

Max Activating Token Index: 188

Text #6

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.5825. Min Act: -0.0000

Data Index: 381838 (C4 (Web Text))

Max Activating Token Index: 644

Text #7

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.6351. Min Act: -0.0000

Data Index: 470430 (C4 (Web Text))

Max Activating Token Index: 859

Text #8

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.5990. Min Act: -0.0001

Data Index: 1268809 (C4 (Web Text))

Max Activating Token Index: 799

Text #9

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.5772. Min Act: -0.0000

Data Index: 403883 (C4 (Web Text))

Max Activating Token Index: 261

Text #10

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.5857. Min Act: -0.0000

Data Index: 805498 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.5676. Min Act: -0.0001

Data Index: 139549 (C4 (Web Text))

Max Activating Token Index: 961

Text #12

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.5846. Min Act: -0.0001

Data Index: 935572 (C4 (Web Text))

Max Activating Token Index: 448

Text #13

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.5604. Min Act: -0.0001

Data Index: 476138 (C4 (Web Text))

Max Activating Token Index: 394

Text #14

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.5535. Min Act: -0.0000

Data Index: 407525 (C4 (Web Text))

Max Activating Token Index: 189

Text #15

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.5519. Min Act: -0.0000

Data Index: 28567 (C4 (Web Text))

Max Activating Token Index: 777

Text #16

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.5659. Min Act: -0.0000

Data Index: 1247066 (C4 (Web Text))

Max Activating Token Index: 665

Text #17

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.5674. Min Act: -0.0000

Data Index: 1223647 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.5615. Min Act: -0.0001

Data Index: 16507 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.5699. Min Act: -0.0000

Data Index: 1109259 (C4 (Web Text))

Max Activating Token Index: 302