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

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

Neuron 2440 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: 0.5494. Min Range: -0.5494

Max Act: 0.5391. Min Act: -0.0001

Data Index: 833059 (C4 (Web Text))

Max Activating Token Index: 686

Text #1

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.5494. Min Act: -0.0001

Data Index: 927416 (C4 (Web Text))

Max Activating Token Index: 908

Text #2

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.5475. Min Act: -0.0001

Data Index: 181765 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.5411. Min Act: -0.0001

Data Index: 1350433 (C4 (Web Text))

Max Activating Token Index: 191

Text #4

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.5219. Min Act: -0.0001

Data Index: 336588 (C4 (Web Text))

Max Activating Token Index: 931

Text #5

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.5145. Min Act: -0.0001

Data Index: 1039215 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.5158. Min Act: -0.0001

Data Index: 163435 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.5058. Min Act: -0.0001

Data Index: 115380 (C4 (Web Text))

Max Activating Token Index: 584

Text #8

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.5215. Min Act: -0.0001

Data Index: 767469 (C4 (Web Text))

Max Activating Token Index: 575

Text #9

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.5014. Min Act: -0.0001

Data Index: 619916 (C4 (Web Text))

Max Activating Token Index: 165

Text #10

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.4807. Min Act: -0.0001

Data Index: 638870 (C4 (Web Text))

Max Activating Token Index: 701

Text #11

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.4860. Min Act: -0.0001

Data Index: 1210171 (C4 (Web Text))

Max Activating Token Index: 696

Text #12

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.4654. Min Act: -0.0001

Data Index: 705565 (C4 (Web Text))

Max Activating Token Index: 278

Text #13

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.5000. Min Act: -0.0001

Data Index: 434513 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.4767. Min Act: -0.0001

Data Index: 17593 (C4 (Web Text))

Max Activating Token Index: 805

Text #15

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.4652. Min Act: -0.0001

Data Index: 1132776 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.4835. Min Act: -0.0001

Data Index: 930446 (C4 (Web Text))

Max Activating Token Index: 865

Text #17

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.4610. Min Act: -0.0001

Data Index: 989196 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.4627. Min Act: -0.0001

Data Index: 1139246 (C4 (Web Text))

Max Activating Token Index: 224

Text #19

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.4759. Min Act: -0.0001

Data Index: 525655 (C4 (Web Text))

Max Activating Token Index: 332