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

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

Neuron 3196 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: 0.7814. Min Range: -0.7814

Max Act: 0.7814. Min Act: -0.0000

Data Index: 372995 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 0.7814. Min Range: -0.7814

Max Act: 0.6292. Min Act: -0.0000

Data Index: 582298 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 0.7814. Min Range: -0.7814

Max Act: 0.6228. Min Act: -0.0000

Data Index: 583027 (C4 (Web Text))

Max Activating Token Index: 230

Text #3

Max Range: 0.7814. Min Range: -0.7814

Max Act: 0.6109. Min Act: -0.0000

Data Index: 326195 (C4 (Web Text))

Max Activating Token Index: 690

Text #4

Max Range: 0.7814. Min Range: -0.7814

Max Act: 0.5583. Min Act: -0.0000

Data Index: 805613 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 0.7814. Min Range: -0.7814

Max Act: 0.5470. Min Act: -0.0000

Data Index: 451199 (C4 (Web Text))

Max Activating Token Index: 521

Text #6

Max Range: 0.7814. Min Range: -0.7814

Max Act: 0.5307. Min Act: -0.0000

Data Index: 618199 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 0.7814. Min Range: -0.7814

Max Act: 0.5318. Min Act: 0.0000

Data Index: 1020586 (C4 (Web Text))

Max Activating Token Index: 923

Text #8

Max Range: 0.7814. Min Range: -0.7814

Max Act: 0.5286. Min Act: -0.0000

Data Index: 567465 (C4 (Web Text))

Max Activating Token Index: 841

Text #9

Max Range: 0.7814. Min Range: -0.7814

Max Act: 0.5174. Min Act: 0.0000

Data Index: 162928 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 0.7814. Min Range: -0.7814

Max Act: 0.5158. Min Act: -0.0000

Data Index: 34337 (C4 (Web Text))

Max Activating Token Index: 774

Text #11

Max Range: 0.7814. Min Range: -0.7814

Max Act: 0.4248. Min Act: -0.0000

Data Index: 543017 (C4 (Web Text))

Max Activating Token Index: 740

Text #12

Max Range: 0.7814. Min Range: -0.7814

Max Act: 0.4827. Min Act: -0.0000

Data Index: 68603 (C4 (Web Text))

Max Activating Token Index: 832

Text #13

Max Range: 0.7814. Min Range: -0.7814

Max Act: 0.4540. Min Act: -0.0000

Data Index: 69511 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 0.7814. Min Range: -0.7814

Max Act: 0.4414. Min Act: -0.0000

Data Index: 928301 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 0.7814. Min Range: -0.7814

Max Act: 0.4736. Min Act: -0.0000

Data Index: 1326033 (C4 (Web Text))

Max Activating Token Index: 1020

Text #16

Max Range: 0.7814. Min Range: -0.7814

Max Act: 0.4754. Min Act: -0.0000

Data Index: 890276 (C4 (Web Text))

Max Activating Token Index: 647

Text #17

Max Range: 0.7814. Min Range: -0.7814

Max Act: 0.4611. Min Act: -0.0000

Data Index: 26648 (C4 (Web Text))

Max Activating Token Index: 738

Text #18

Max Range: 0.7814. Min Range: -0.7814

Max Act: 0.4744. Min Act: 0.0000

Data Index: 404124 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 0.7814. Min Range: -0.7814

Max Act: 0.4753. Min Act: -0.0000

Data Index: 97886 (C4 (Web Text))

Max Activating Token Index: 960