Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 85 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0985. Min Range: -1.0985

Max Act: 1.0779. Min Act: -0.0001

Data Index: 777633 (C4 (Web Text))

Max Activating Token Index: 490

Text #1

Max Range: 1.0985. Min Range: -1.0985

Max Act: 0.9705. Min Act: -0.0001

Data Index: 1040650 (C4 (Web Text))

Max Activating Token Index: 745

Text #2

Max Range: 1.0985. Min Range: -1.0985

Max Act: 0.9841. Min Act: -0.0001

Data Index: 408996 (C4 (Web Text))

Max Activating Token Index: 283

Text #3

Max Range: 1.0985. Min Range: -1.0985

Max Act: 0.9201. Min Act: -0.0001

Data Index: 102235 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 1.0985. Min Range: -1.0985

Max Act: 0.9666. Min Act: -0.0001

Data Index: 1340418 (C4 (Web Text))

Max Activating Token Index: 164

Text #5

Max Range: 1.0985. Min Range: -1.0985

Max Act: 1.0985. Min Act: -0.0001

Data Index: 682397 (C4 (Web Text))

Max Activating Token Index: 944

Text #6

Max Range: 1.0985. Min Range: -1.0985

Max Act: 0.9334. Min Act: -0.0001

Data Index: 845982 (C4 (Web Text))

Max Activating Token Index: 453

Text #7

Max Range: 1.0985. Min Range: -1.0985

Max Act: 0.9577. Min Act: -0.0001

Data Index: 873140 (C4 (Web Text))

Max Activating Token Index: 916

Text #8

Max Range: 1.0985. Min Range: -1.0985

Max Act: 0.9370. Min Act: -0.0001

Data Index: 761737 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 1.0985. Min Range: -1.0985

Max Act: 0.8720. Min Act: -0.0001

Data Index: 1028290 (C4 (Web Text))

Max Activating Token Index: 335

Text #10

Max Range: 1.0985. Min Range: -1.0985

Max Act: 0.8187. Min Act: -0.0001

Data Index: 1051708 (C4 (Web Text))

Max Activating Token Index: 337

Text #11

Max Range: 1.0985. Min Range: -1.0985

Max Act: 0.7652. Min Act: -0.0001

Data Index: 920061 (C4 (Web Text))

Max Activating Token Index: 508

Text #12

Max Range: 1.0985. Min Range: -1.0985

Max Act: 0.7983. Min Act: -0.0001

Data Index: 346072 (C4 (Web Text))

Max Activating Token Index: 738

Text #13

Max Range: 1.0985. Min Range: -1.0985

Max Act: 0.8103. Min Act: -0.0001

Data Index: 45443 (C4 (Web Text))

Max Activating Token Index: 450

Text #14

Max Range: 1.0985. Min Range: -1.0985

Max Act: 0.8231. Min Act: -0.0001

Data Index: 848493 (C4 (Web Text))

Max Activating Token Index: 625

Text #15

Max Range: 1.0985. Min Range: -1.0985

Max Act: 0.7253. Min Act: -0.0001

Data Index: 245041 (C4 (Web Text))

Max Activating Token Index: 967

Text #16

Max Range: 1.0985. Min Range: -1.0985

Max Act: 0.8032. Min Act: -0.0001

Data Index: 211662 (C4 (Web Text))

Max Activating Token Index: 72

Text #17

Max Range: 1.0985. Min Range: -1.0985

Max Act: 0.8523. Min Act: -0.0001

Data Index: 1274791 (C4 (Web Text))

Max Activating Token Index: 760

Text #18

Max Range: 1.0985. Min Range: -1.0985

Max Act: 0.7549. Min Act: -0.0001

Data Index: 1039421 (C4 (Web Text))

Max Activating Token Index: 248

Text #19

Max Range: 1.0985. Min Range: -1.0985

Max Act: 0.7755. Min Act: -0.0001

Data Index: 86505 (C4 (Web Text))

Max Activating Token Index: 638