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

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

Neuron 168 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3480. Min Range: -1.3480

Max Act: 1.3480. Min Act: -0.0000

Data Index: 735237 (C4 (Web Text))

Max Activating Token Index: 753

Text #1

Max Range: 1.3480. Min Range: -1.3480

Max Act: 1.1310. Min Act: -0.0000

Data Index: 592380 (C4 (Web Text))

Max Activating Token Index: 92

Text #2

Max Range: 1.3480. Min Range: -1.3480

Max Act: 0.9959. Min Act: -0.0000

Data Index: 269324 (C4 (Web Text))

Max Activating Token Index: 639

Text #3

Max Range: 1.3480. Min Range: -1.3480

Max Act: 1.0003. Min Act: -0.0000

Data Index: 931173 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 1.3480. Min Range: -1.3480

Max Act: 0.9230. Min Act: -0.0000

Data Index: 890209 (C4 (Web Text))

Max Activating Token Index: 350

Text #5

Max Range: 1.3480. Min Range: -1.3480

Max Act: 0.8948. Min Act: -0.0000

Data Index: 811543 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 1.3480. Min Range: -1.3480

Max Act: 0.9648. Min Act: -0.0000

Data Index: 387110 (C4 (Web Text))

Max Activating Token Index: 726

Text #7

Max Range: 1.3480. Min Range: -1.3480

Max Act: 0.8838. Min Act: -0.0000

Data Index: 462448 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 1.3480. Min Range: -1.3480

Max Act: 0.8863. Min Act: -0.0000

Data Index: 681578 (C4 (Web Text))

Max Activating Token Index: 929

Text #9

Max Range: 1.3480. Min Range: -1.3480

Max Act: 0.8347. Min Act: -0.0000

Data Index: 5505 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 1.3480. Min Range: -1.3480

Max Act: 0.8763. Min Act: -0.0000

Data Index: 394 (C4 (Web Text))

Max Activating Token Index: 701

Text #11

Max Range: 1.3480. Min Range: -1.3480

Max Act: 0.8386. Min Act: -0.0000

Data Index: 414589 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 1.3480. Min Range: -1.3480

Max Act: 0.8306. Min Act: -0.0000

Data Index: 129630 (C4 (Web Text))

Max Activating Token Index: 595

Text #13

Max Range: 1.3480. Min Range: -1.3480

Max Act: 0.8345. Min Act: -0.0000

Data Index: 1011992 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 1.3480. Min Range: -1.3480

Max Act: 0.8808. Min Act: -0.0000

Data Index: 139417 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 1.3480. Min Range: -1.3480

Max Act: 0.8929. Min Act: -0.0000

Data Index: 1216130 (C4 (Web Text))

Max Activating Token Index: 871

Text #16

Max Range: 1.3480. Min Range: -1.3480

Max Act: 0.8455. Min Act: -0.0000

Data Index: 1158094 (C4 (Web Text))

Max Activating Token Index: 610

Text #17

Max Range: 1.3480. Min Range: -1.3480

Max Act: 0.8443. Min Act: -0.0000

Data Index: 1037362 (C4 (Web Text))

Max Activating Token Index: 589

Text #18

Max Range: 1.3480. Min Range: -1.3480

Max Act: 0.8636. Min Act: -0.0000

Data Index: 1124762 (C4 (Web Text))

Max Activating Token Index: 379

Text #19

Max Range: 1.3480. Min Range: -1.3480

Max Act: 0.8336. Min Act: -0.0000

Data Index: 54965 (C4 (Web Text))

Max Activating Token Index: 270