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

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

Neuron 3606 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3171. Min Range: -5.3171

Max Act: 5.0075. Min Act: -0.0000

Data Index: 543280 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 5.3171. Min Range: -5.3171

Max Act: 5.3171. Min Act: -0.0000

Data Index: 228411 (C4 (Web Text))

Max Activating Token Index: 905

Text #2

Max Range: 5.3171. Min Range: -5.3171

Max Act: 5.0129. Min Act: -0.0000

Data Index: 1300304 (C4 (Web Text))

Max Activating Token Index: 652

Text #3

Max Range: 5.3171. Min Range: -5.3171

Max Act: 4.8017. Min Act: -0.0000

Data Index: 355547 (C4 (Web Text))

Max Activating Token Index: 640

Text #4

Max Range: 5.3171. Min Range: -5.3171

Max Act: 4.8049. Min Act: -0.0000

Data Index: 1050855 (C4 (Web Text))

Max Activating Token Index: 620

Text #5

Max Range: 5.3171. Min Range: -5.3171

Max Act: 4.6731. Min Act: -0.0000

Data Index: 423208 (C4 (Web Text))

Max Activating Token Index: 755

Text #6

Max Range: 5.3171. Min Range: -5.3171

Max Act: 4.4971. Min Act: -0.0000

Data Index: 886975 (C4 (Web Text))

Max Activating Token Index: 619

Text #7

Max Range: 5.3171. Min Range: -5.3171

Max Act: 4.5129. Min Act: -0.0000

Data Index: 785667 (C4 (Web Text))

Max Activating Token Index: 802

Text #8

Max Range: 5.3171. Min Range: -5.3171

Max Act: 4.4755. Min Act: -0.0000

Data Index: 33237 (C4 (Web Text))

Max Activating Token Index: 612

Text #9

Max Range: 5.3171. Min Range: -5.3171

Max Act: 4.4355. Min Act: -0.0000

Data Index: 291746 (C4 (Web Text))

Max Activating Token Index: 747

Text #10

Max Range: 5.3171. Min Range: -5.3171

Max Act: 4.3335. Min Act: -0.0000

Data Index: 290839 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 5.3171. Min Range: -5.3171

Max Act: 4.0703. Min Act: -0.0000

Data Index: 1200200 (C4 (Web Text))

Max Activating Token Index: 902

Text #12

Max Range: 5.3171. Min Range: -5.3171

Max Act: 4.4162. Min Act: -0.0000

Data Index: 701675 (C4 (Web Text))

Max Activating Token Index: 83

Text #13

Max Range: 5.3171. Min Range: -5.3171

Max Act: 4.2352. Min Act: -0.0000

Data Index: 235375 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 5.3171. Min Range: -5.3171

Max Act: 4.1896. Min Act: -0.0000

Data Index: 74900 (C4 (Web Text))

Max Activating Token Index: 602

Text #15

Max Range: 5.3171. Min Range: -5.3171

Max Act: 4.1813. Min Act: -0.0000

Data Index: 541174 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 5.3171. Min Range: -5.3171

Max Act: 4.1394. Min Act: -0.0000

Data Index: 708384 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 5.3171. Min Range: -5.3171

Max Act: 4.1025. Min Act: -0.0000

Data Index: 797410 (C4 (Web Text))

Max Activating Token Index: 763

Text #18

Max Range: 5.3171. Min Range: -5.3171

Max Act: 4.2721. Min Act: -0.0000

Data Index: 643880 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 5.3171. Min Range: -5.3171

Max Act: 4.2384. Min Act: -0.0000

Data Index: 1198412 (C4 (Web Text))

Max Activating Token Index: 661