Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5394 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 8.0775. Min Range: -8.0775

Max Act: 8.0775. Min Act: -0.0000

Data Index: 398183 (C4 (Web Text))

Max Activating Token Index: 704

Text #1

Max Range: 8.0775. Min Range: -8.0775

Max Act: 7.1800. Min Act: -0.0000

Data Index: 459754 (C4 (Web Text))

Max Activating Token Index: 394

Text #2

Max Range: 8.0775. Min Range: -8.0775

Max Act: 7.3250. Min Act: -0.0000

Data Index: 163534 (C4 (Web Text))

Max Activating Token Index: 289

Text #3

Max Range: 8.0775. Min Range: -8.0775

Max Act: 7.0951. Min Act: -0.0000

Data Index: 951893 (C4 (Web Text))

Max Activating Token Index: 711

Text #4

Max Range: 8.0775. Min Range: -8.0775

Max Act: 6.9230. Min Act: -0.0000

Data Index: 671937 (C4 (Web Text))

Max Activating Token Index: 390

Text #5

Max Range: 8.0775. Min Range: -8.0775

Max Act: 7.1154. Min Act: -0.0000

Data Index: 305905 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 8.0775. Min Range: -8.0775

Max Act: 6.5702. Min Act: -0.0000

Data Index: 788947 (C4 (Web Text))

Max Activating Token Index: 939

Text #7

Max Range: 8.0775. Min Range: -8.0775

Max Act: 6.5717. Min Act: -0.0000

Data Index: 268695 (C4 (Web Text))

Max Activating Token Index: 522

Text #8

Max Range: 8.0775. Min Range: -8.0775

Max Act: 6.1624. Min Act: -0.0000

Data Index: 1167303 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 8.0775. Min Range: -8.0775

Max Act: 6.4747. Min Act: -0.0001

Data Index: 733809 (C4 (Web Text))

Max Activating Token Index: 427

Text #10

Max Range: 8.0775. Min Range: -8.0775

Max Act: 6.4878. Min Act: -0.0000

Data Index: 845166 (C4 (Web Text))

Max Activating Token Index: 472

Text #11

Max Range: 8.0775. Min Range: -8.0775

Max Act: 6.2697. Min Act: -0.0001

Data Index: 1358937 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 8.0775. Min Range: -8.0775

Max Act: 6.4236. Min Act: -0.0000

Data Index: 257453 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 8.0775. Min Range: -8.0775

Max Act: 6.3850. Min Act: -0.0000

Data Index: 804565 (C4 (Web Text))

Max Activating Token Index: 183

Text #14

Max Range: 8.0775. Min Range: -8.0775

Max Act: 6.4456. Min Act: -0.0000

Data Index: 843545 (C4 (Web Text))

Max Activating Token Index: 722

Text #15

Max Range: 8.0775. Min Range: -8.0775

Max Act: 6.2734. Min Act: -0.0000

Data Index: 630513 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 8.0775. Min Range: -8.0775

Max Act: 6.0230. Min Act: -0.0000

Data Index: 1348478 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 8.0775. Min Range: -8.0775

Max Act: 6.0104. Min Act: -0.0000

Data Index: 149465 (C4 (Web Text))

Max Activating Token Index: 532

Text #18

Max Range: 8.0775. Min Range: -8.0775

Max Act: 6.1720. Min Act: -0.0000

Data Index: 964694 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 8.0775. Min Range: -8.0775

Max Act: 5.9899. Min Act: -0.0000

Data Index: 247763 (C4 (Web Text))

Max Activating Token Index: 459