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

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

Neuron 4538 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: 3.8630. Min Range: -3.8630

Max Act: 3.8630. Min Act: -0.0000

Data Index: 302039 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 3.8630. Min Range: -3.8630

Max Act: 3.7696. Min Act: -0.0000

Data Index: 468477 (C4 (Web Text))

Max Activating Token Index: 251

Text #2

Max Range: 3.8630. Min Range: -3.8630

Max Act: 3.5909. Min Act: -0.0000

Data Index: 185105 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 3.8630. Min Range: -3.8630

Max Act: 3.2738. Min Act: -0.0000

Data Index: 494674 (C4 (Web Text))

Max Activating Token Index: 135

Text #4

Max Range: 3.8630. Min Range: -3.8630

Max Act: 3.0734. Min Act: -0.0000

Data Index: 706501 (C4 (Web Text))

Max Activating Token Index: 914

Text #5

Max Range: 3.8630. Min Range: -3.8630

Max Act: 3.1887. Min Act: -0.0000

Data Index: 1225006 (C4 (Web Text))

Max Activating Token Index: 998

Text #6

Max Range: 3.8630. Min Range: -3.8630

Max Act: 3.1314. Min Act: -0.0000

Data Index: 1224007 (C4 (Web Text))

Max Activating Token Index: 652

Text #7

Max Range: 3.8630. Min Range: -3.8630

Max Act: 3.0440. Min Act: -0.0000

Data Index: 498627 (C4 (Web Text))

Max Activating Token Index: 907

Text #8

Max Range: 3.8630. Min Range: -3.8630

Max Act: 3.0273. Min Act: -0.0000

Data Index: 965486 (C4 (Web Text))

Max Activating Token Index: 133

Text #9

Max Range: 3.8630. Min Range: -3.8630

Max Act: 3.1755. Min Act: 0.0000

Data Index: 1351850 (C4 (Web Text))

Max Activating Token Index: 700

Text #10

Max Range: 3.8630. Min Range: -3.8630

Max Act: 3.0742. Min Act: -0.0000

Data Index: 1129446 (C4 (Web Text))

Max Activating Token Index: 931

Text #11

Max Range: 3.8630. Min Range: -3.8630

Max Act: 2.7516. Min Act: -0.0000

Data Index: 1153157 (C4 (Web Text))

Max Activating Token Index: 255

Text #12

Max Range: 3.8630. Min Range: -3.8630

Max Act: 2.8767. Min Act: -0.0000

Data Index: 794804 (C4 (Web Text))

Max Activating Token Index: 426

Text #13

Max Range: 3.8630. Min Range: -3.8630

Max Act: 3.0158. Min Act: -0.0000

Data Index: 960543 (C4 (Web Text))

Max Activating Token Index: 936

Text #14

Max Range: 3.8630. Min Range: -3.8630

Max Act: 3.1181. Min Act: -0.0000

Data Index: 293127 (C4 (Web Text))

Max Activating Token Index: 704

Text #15

Max Range: 3.8630. Min Range: -3.8630

Max Act: 2.8231. Min Act: 0.0000

Data Index: 119784 (C4 (Web Text))

Max Activating Token Index: 946

Text #16

Max Range: 3.8630. Min Range: -3.8630

Max Act: 2.7893. Min Act: -0.0000

Data Index: 613622 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 3.8630. Min Range: -3.8630

Max Act: 2.6461. Min Act: -0.0000

Data Index: 93608 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 3.8630. Min Range: -3.8630

Max Act: 2.7849. Min Act: -0.0000

Data Index: 887317 (C4 (Web Text))

Max Activating Token Index: 335

Text #19

Max Range: 3.8630. Min Range: -3.8630

Max Act: 2.7806. Min Act: 0.0000

Data Index: 772766 (C4 (Web Text))

Max Activating Token Index: 326