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

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

Neuron 5068 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: 3.9122. Min Range: -3.9122

Max Act: 3.9122. Min Act: -0.0000

Data Index: 593849 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 3.9122. Min Range: -3.9122

Max Act: 3.8681. Min Act: -0.0000

Data Index: 1052498 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 3.9122. Min Range: -3.9122

Max Act: 3.4365. Min Act: -0.0000

Data Index: 437443 (C4 (Web Text))

Max Activating Token Index: 666

Text #3

Max Range: 3.9122. Min Range: -3.9122

Max Act: 3.1016. Min Act: -0.0000

Data Index: 441056 (C4 (Web Text))

Max Activating Token Index: 929

Text #4

Max Range: 3.9122. Min Range: -3.9122

Max Act: 3.1143. Min Act: -0.0000

Data Index: 333108 (C4 (Web Text))

Max Activating Token Index: 862

Text #5

Max Range: 3.9122. Min Range: -3.9122

Max Act: 2.8785. Min Act: -0.0000

Data Index: 681125 (C4 (Web Text))

Max Activating Token Index: 755

Text #6

Max Range: 3.9122. Min Range: -3.9122

Max Act: 2.9354. Min Act: -0.0000

Data Index: 991885 (C4 (Web Text))

Max Activating Token Index: 499

Text #7

Max Range: 3.9122. Min Range: -3.9122

Max Act: 2.9362. Min Act: -0.0000

Data Index: 1141411 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 3.9122. Min Range: -3.9122

Max Act: 2.8727. Min Act: -0.0000

Data Index: 1102172 (C4 (Web Text))

Max Activating Token Index: 255

Text #9

Max Range: 3.9122. Min Range: -3.9122

Max Act: 2.8142. Min Act: -0.0000

Data Index: 383529 (C4 (Web Text))

Max Activating Token Index: 518

Text #10

Max Range: 3.9122. Min Range: -3.9122

Max Act: 2.6092. Min Act: -0.0000

Data Index: 359308 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 3.9122. Min Range: -3.9122

Max Act: 2.5641. Min Act: -0.0000

Data Index: 10420 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 3.9122. Min Range: -3.9122

Max Act: 2.6811. Min Act: -0.0000

Data Index: 550392 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 3.9122. Min Range: -3.9122

Max Act: 2.6489. Min Act: -0.0000

Data Index: 731171 (C4 (Web Text))

Max Activating Token Index: 829

Text #14

Max Range: 3.9122. Min Range: -3.9122

Max Act: 2.5778. Min Act: -0.0000

Data Index: 339698 (C4 (Web Text))

Max Activating Token Index: 761

Text #15

Max Range: 3.9122. Min Range: -3.9122

Max Act: 2.5731. Min Act: -0.0000

Data Index: 747686 (C4 (Web Text))

Max Activating Token Index: 562

Text #16

Max Range: 3.9122. Min Range: -3.9122

Max Act: 2.4179. Min Act: -0.0000

Data Index: 1257046 (C4 (Web Text))

Max Activating Token Index: 509

Text #17

Max Range: 3.9122. Min Range: -3.9122

Max Act: 2.5521. Min Act: -0.0000

Data Index: 799917 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 3.9122. Min Range: -3.9122

Max Act: 2.5406. Min Act: -0.0000

Data Index: 494200 (C4 (Web Text))

Max Activating Token Index: 763

Text #19

Max Range: 3.9122. Min Range: -3.9122

Max Act: 2.6654. Min Act: -0.0000

Data Index: 612087 (C4 (Web Text))

Max Activating Token Index: 579