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

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

Neuron 2525 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4997. Min Range: -0.4997

Max Act: 0.4997. Min Act: -0.0001

Data Index: 646345 (C4 (Web Text))

Max Activating Token Index: 582

Text #1

Max Range: 0.4997. Min Range: -0.4997

Max Act: 0.4599. Min Act: -0.0001

Data Index: 1252399 (C4 (Web Text))

Max Activating Token Index: 277

Text #2

Max Range: 0.4997. Min Range: -0.4997

Max Act: 0.4042. Min Act: -0.0001

Data Index: 477507 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 0.4997. Min Range: -0.4997

Max Act: 0.4039. Min Act: -0.0001

Data Index: 1328841 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 0.4997. Min Range: -0.4997

Max Act: 0.3823. Min Act: -0.0001

Data Index: 273243 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 0.4997. Min Range: -0.4997

Max Act: 0.3887. Min Act: -0.0001

Data Index: 522102 (C4 (Web Text))

Max Activating Token Index: 492

Text #6

Max Range: 0.4997. Min Range: -0.4997

Max Act: 0.3728. Min Act: -0.0001

Data Index: 272689 (C4 (Web Text))

Max Activating Token Index: 533

Text #7

Max Range: 0.4997. Min Range: -0.4997

Max Act: 0.3801. Min Act: -0.0001

Data Index: 714231 (C4 (Web Text))

Max Activating Token Index: 746

Text #8

Max Range: 0.4997. Min Range: -0.4997

Max Act: 0.4023. Min Act: -0.0001

Data Index: 943124 (C4 (Web Text))

Max Activating Token Index: 550

Text #9

Max Range: 0.4997. Min Range: -0.4997

Max Act: 0.3861. Min Act: -0.0001

Data Index: 11146 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 0.4997. Min Range: -0.4997

Max Act: 0.3846. Min Act: -0.0001

Data Index: 552755 (C4 (Web Text))

Max Activating Token Index: 470

Text #11

Max Range: 0.4997. Min Range: -0.4997

Max Act: 0.3822. Min Act: -0.0001

Data Index: 284426 (C4 (Web Text))

Max Activating Token Index: 750

Text #12

Max Range: 0.4997. Min Range: -0.4997

Max Act: 0.3832. Min Act: -0.0001

Data Index: 408637 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 0.4997. Min Range: -0.4997

Max Act: 0.3746. Min Act: -0.0001

Data Index: 632315 (C4 (Web Text))

Max Activating Token Index: 156

Text #14

Max Range: 0.4997. Min Range: -0.4997

Max Act: 0.3599. Min Act: -0.0001

Data Index: 695469 (C4 (Web Text))

Max Activating Token Index: 974

Text #15

Max Range: 0.4997. Min Range: -0.4997

Max Act: 0.3590. Min Act: -0.0001

Data Index: 436469 (C4 (Web Text))

Max Activating Token Index: 481

Text #16

Max Range: 0.4997. Min Range: -0.4997

Max Act: 0.3718. Min Act: -0.0001

Data Index: 113788 (C4 (Web Text))

Max Activating Token Index: 590

Text #17

Max Range: 0.4997. Min Range: -0.4997

Max Act: 0.3807. Min Act: -0.0001

Data Index: 136442 (C4 (Web Text))

Max Activating Token Index: 401

Text #18

Max Range: 0.4997. Min Range: -0.4997

Max Act: 0.3703. Min Act: -0.0001

Data Index: 365012 (C4 (Web Text))

Max Activating Token Index: 419

Text #19

Max Range: 0.4997. Min Range: -0.4997

Max Act: 0.3573. Min Act: -0.0001

Data Index: 865724 (C4 (Web Text))

Max Activating Token Index: 896