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

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

Neuron 5204 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5147. Min Range: -0.5147

Max Act: 0.5076. Min Act: -0.0000

Data Index: 1295703 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 0.5147. Min Range: -0.5147

Max Act: 0.5010. Min Act: -0.0000

Data Index: 654834 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 0.5147. Min Range: -0.5147

Max Act: 0.5147. Min Act: -0.0000

Data Index: 1041198 (C4 (Web Text))

Max Activating Token Index: 143

Text #3

Max Range: 0.5147. Min Range: -0.5147

Max Act: 0.4767. Min Act: -0.0000

Data Index: 433217 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 0.5147. Min Range: -0.5147

Max Act: 0.4742. Min Act: -0.0000

Data Index: 571485 (C4 (Web Text))

Max Activating Token Index: 850

Text #5

Max Range: 0.5147. Min Range: -0.5147

Max Act: 0.4432. Min Act: -0.0000

Data Index: 423344 (C4 (Web Text))

Max Activating Token Index: 605

Text #6

Max Range: 0.5147. Min Range: -0.5147

Max Act: 0.4593. Min Act: -0.0000

Data Index: 260731 (C4 (Web Text))

Max Activating Token Index: 632

Text #7

Max Range: 0.5147. Min Range: -0.5147

Max Act: 0.4205. Min Act: -0.0000

Data Index: 846050 (C4 (Web Text))

Max Activating Token Index: 228

Text #8

Max Range: 0.5147. Min Range: -0.5147

Max Act: 0.4540. Min Act: -0.0000

Data Index: 754757 (C4 (Web Text))

Max Activating Token Index: 361

Text #9

Max Range: 0.5147. Min Range: -0.5147

Max Act: 0.4526. Min Act: -0.0000

Data Index: 1159182 (C4 (Web Text))

Max Activating Token Index: 494

Text #10

Max Range: 0.5147. Min Range: -0.5147

Max Act: 0.4270. Min Act: -0.0000

Data Index: 136825 (C4 (Web Text))

Max Activating Token Index: 667

Text #11

Max Range: 0.5147. Min Range: -0.5147

Max Act: 0.4531. Min Act: -0.0000

Data Index: 1211743 (C4 (Web Text))

Max Activating Token Index: 525

Text #12

Max Range: 0.5147. Min Range: -0.5147

Max Act: 0.4334. Min Act: -0.0000

Data Index: 1195223 (C4 (Web Text))

Max Activating Token Index: 470

Text #13

Max Range: 0.5147. Min Range: -0.5147

Max Act: 0.4197. Min Act: -0.0000

Data Index: 1141193 (C4 (Web Text))

Max Activating Token Index: 771

Text #14

Max Range: 0.5147. Min Range: -0.5147

Max Act: 0.4028. Min Act: -0.0000

Data Index: 1050800 (C4 (Web Text))

Max Activating Token Index: 945

Text #15

Max Range: 0.5147. Min Range: -0.5147

Max Act: 0.4105. Min Act: -0.0000

Data Index: 838045 (C4 (Web Text))

Max Activating Token Index: 468

Text #16

Max Range: 0.5147. Min Range: -0.5147

Max Act: 0.4159. Min Act: -0.0000

Data Index: 890801 (C4 (Web Text))

Max Activating Token Index: 911

Text #17

Max Range: 0.5147. Min Range: -0.5147

Max Act: 0.4186. Min Act: -0.0000

Data Index: 88042 (C4 (Web Text))

Max Activating Token Index: 837

Text #18

Max Range: 0.5147. Min Range: -0.5147

Max Act: 0.4269. Min Act: -0.0000

Data Index: 24825 (C4 (Web Text))

Max Activating Token Index: 847

Text #19

Max Range: 0.5147. Min Range: -0.5147

Max Act: 0.4120. Min Act: -0.0000

Data Index: 29892 (C4 (Web Text))

Max Activating Token Index: 622