Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3930 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.8471. Min Act: -0.0000

Data Index: 155843 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.6849. Min Act: -0.0000

Data Index: 1280209 (C4 (Web Text))

Max Activating Token Index: 780

Text #2

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.6061. Min Act: -0.0000

Data Index: 1088392 (C4 (Web Text))

Max Activating Token Index: 619

Text #3

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.5864. Min Act: -0.0000

Data Index: 909243 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.6309. Min Act: -0.0000

Data Index: 1339123 (C4 (Web Text))

Max Activating Token Index: 823

Text #5

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.5925. Min Act: -0.0000

Data Index: 1175272 (C4 (Web Text))

Max Activating Token Index: 1012

Text #6

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.5856. Min Act: -0.0000

Data Index: 519776 (C4 (Web Text))

Max Activating Token Index: 457

Text #7

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.5311. Min Act: -0.0000

Data Index: 456014 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.4689. Min Act: -0.0000

Data Index: 1036219 (C4 (Web Text))

Max Activating Token Index: 568

Text #9

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.4645. Min Act: -0.0000

Data Index: 135578 (C4 (Web Text))

Max Activating Token Index: 983

Text #10

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.4924. Min Act: -0.0000

Data Index: 219727 (C4 (Web Text))

Max Activating Token Index: 803

Text #11

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.4439. Min Act: -0.0000

Data Index: 754710 (C4 (Web Text))

Max Activating Token Index: 804

Text #12

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.4416. Min Act: -0.0000

Data Index: 487615 (C4 (Web Text))

Max Activating Token Index: 896

Text #13

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.4157. Min Act: -0.0000

Data Index: 1054070 (C4 (Web Text))

Max Activating Token Index: 799

Text #14

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.4225. Min Act: -0.0000

Data Index: 135731 (C4 (Web Text))

Max Activating Token Index: 433

Text #15

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.4012. Min Act: -0.0000

Data Index: 1166742 (C4 (Web Text))

Max Activating Token Index: 819

Text #16

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.4367. Min Act: -0.0000

Data Index: 53483 (C4 (Web Text))

Max Activating Token Index: 136

Text #17

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.4341. Min Act: -0.0000

Data Index: 228417 (C4 (Web Text))

Max Activating Token Index: 949

Text #18

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.4265. Min Act: -0.0000

Data Index: 1133697 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.4275. Min Act: -0.0000

Data Index: 177034 (C4 (Web Text))

Max Activating Token Index: 255