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

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

Neuron 2567 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: 0.8334. Min Range: -0.8334

Max Act: 0.8334. Min Act: -0.0001

Data Index: 989000 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 0.8334. Min Range: -0.8334

Max Act: 0.7850. Min Act: -0.0000

Data Index: 777379 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 0.8334. Min Range: -0.8334

Max Act: 0.7433. Min Act: -0.0000

Data Index: 439268 (C4 (Web Text))

Max Activating Token Index: 286

Text #3

Max Range: 0.8334. Min Range: -0.8334

Max Act: 0.6978. Min Act: -0.0001

Data Index: 1294003 (C4 (Web Text))

Max Activating Token Index: 891

Text #4

Max Range: 0.8334. Min Range: -0.8334

Max Act: 0.7363. Min Act: -0.0000

Data Index: 688849 (C4 (Web Text))

Max Activating Token Index: 979

Text #5

Max Range: 0.8334. Min Range: -0.8334

Max Act: 0.6809. Min Act: -0.0001

Data Index: 417845 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 0.8334. Min Range: -0.8334

Max Act: 0.7407. Min Act: -0.0001

Data Index: 742595 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 0.8334. Min Range: -0.8334

Max Act: 0.7010. Min Act: -0.0001

Data Index: 457942 (C4 (Web Text))

Max Activating Token Index: 771

Text #8

Max Range: 0.8334. Min Range: -0.8334

Max Act: 0.7167. Min Act: -0.0000

Data Index: 280115 (C4 (Web Text))

Max Activating Token Index: 794

Text #9

Max Range: 0.8334. Min Range: -0.8334

Max Act: 0.7036. Min Act: -0.0000

Data Index: 984672 (C4 (Web Text))

Max Activating Token Index: 430

Text #10

Max Range: 0.8334. Min Range: -0.8334

Max Act: 0.6766. Min Act: -0.0000

Data Index: 148633 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 0.8334. Min Range: -0.8334

Max Act: 0.6733. Min Act: -0.0000

Data Index: 249186 (C4 (Web Text))

Max Activating Token Index: 820

Text #12

Max Range: 0.8334. Min Range: -0.8334

Max Act: 0.6893. Min Act: -0.0001

Data Index: 109004 (C4 (Web Text))

Max Activating Token Index: 800

Text #13

Max Range: 0.8334. Min Range: -0.8334

Max Act: 0.6328. Min Act: -0.0001

Data Index: 832414 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 0.8334. Min Range: -0.8334

Max Act: 0.6716. Min Act: -0.0000

Data Index: 671451 (C4 (Web Text))

Max Activating Token Index: 651

Text #15

Max Range: 0.8334. Min Range: -0.8334

Max Act: 0.6673. Min Act: -0.0001

Data Index: 924733 (C4 (Web Text))

Max Activating Token Index: 817

Text #16

Max Range: 0.8334. Min Range: -0.8334

Max Act: 0.6458. Min Act: -0.0001

Data Index: 686126 (C4 (Web Text))

Max Activating Token Index: 902

Text #17

Max Range: 0.8334. Min Range: -0.8334

Max Act: 0.6652. Min Act: -0.0000

Data Index: 916250 (C4 (Web Text))

Max Activating Token Index: 335

Text #18

Max Range: 0.8334. Min Range: -0.8334

Max Act: 0.6616. Min Act: -0.0001

Data Index: 1250623 (C4 (Web Text))

Max Activating Token Index: 728

Text #19

Max Range: 0.8334. Min Range: -0.8334

Max Act: 0.6177. Min Act: -0.0001

Data Index: 900041 (C4 (Web Text))

Max Activating Token Index: 319