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

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

Neuron 3879 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: 0.0894. Min Range: -0.0894

Max Act: 0.0869. Min Act: -0.0001

Data Index: 482227 (C4 (Web Text))

Max Activating Token Index: 930

Text #1

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0894. Min Act: -0.0001

Data Index: 416446 (C4 (Web Text))

Max Activating Token Index: 845

Text #2

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0848. Min Act: -0.0001

Data Index: 241937 (C4 (Web Text))

Max Activating Token Index: 398

Text #3

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0807. Min Act: -0.0001

Data Index: 550326 (C4 (Web Text))

Max Activating Token Index: 491

Text #4

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0780. Min Act: -0.0001

Data Index: 369101 (C4 (Web Text))

Max Activating Token Index: 814

Text #5

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0654. Min Act: -0.0001

Data Index: 523855 (C4 (Web Text))

Max Activating Token Index: 608

Text #6

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0658. Min Act: -0.0001

Data Index: 973620 (C4 (Web Text))

Max Activating Token Index: 429

Text #7

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0654. Min Act: -0.0001

Data Index: 812529 (C4 (Web Text))

Max Activating Token Index: 953

Text #8

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0683. Min Act: -0.0001

Data Index: 491230 (C4 (Web Text))

Max Activating Token Index: 258

Text #9

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0705. Min Act: -0.0001

Data Index: 1099877 (C4 (Web Text))

Max Activating Token Index: 257

Text #10

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0701. Min Act: -0.0001

Data Index: 95748 (C4 (Web Text))

Max Activating Token Index: 276

Text #11

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0699. Min Act: -0.0001

Data Index: 566464 (C4 (Web Text))

Max Activating Token Index: 500

Text #12

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0677. Min Act: -0.0001

Data Index: 820549 (C4 (Web Text))

Max Activating Token Index: 882

Text #13

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0727. Min Act: -0.0001

Data Index: 963071 (C4 (Web Text))

Max Activating Token Index: 758

Text #14

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0641. Min Act: -0.0001

Data Index: 232436 (C4 (Web Text))

Max Activating Token Index: 905

Text #15

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0641. Min Act: -0.0001

Data Index: 170189 (C4 (Web Text))

Max Activating Token Index: 906

Text #16

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0617. Min Act: -0.0001

Data Index: 134400 (C4 (Web Text))

Max Activating Token Index: 475

Text #17

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0614. Min Act: -0.0001

Data Index: 1329857 (C4 (Web Text))

Max Activating Token Index: 580

Text #18

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0634. Min Act: -0.0001

Data Index: 1058383 (C4 (Web Text))

Max Activating Token Index: 908

Text #19

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0609. Min Act: -0.0001

Data Index: 670463 (C4 (Web Text))

Max Activating Token Index: 350