Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 67 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8155. Min Range: -0.8155

Max Act: 0.8155. Min Act: -0.0001

Data Index: 321878 (C4 (Web Text))

Max Activating Token Index: 606

Text #1

Max Range: 0.8155. Min Range: -0.8155

Max Act: 0.6611. Min Act: -0.0001

Data Index: 725595 (C4 (Web Text))

Max Activating Token Index: 470

Text #2

Max Range: 0.8155. Min Range: -0.8155

Max Act: 0.5941. Min Act: -0.0001

Data Index: 317060 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 0.8155. Min Range: -0.8155

Max Act: 0.5781. Min Act: -0.0001

Data Index: 1081196 (C4 (Web Text))

Max Activating Token Index: 553

Text #4

Max Range: 0.8155. Min Range: -0.8155

Max Act: 0.5748. Min Act: -0.0001

Data Index: 1086607 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 0.8155. Min Range: -0.8155

Max Act: 0.6311. Min Act: -0.0001

Data Index: 598696 (C4 (Web Text))

Max Activating Token Index: 206

Text #6

Max Range: 0.8155. Min Range: -0.8155

Max Act: 0.6518. Min Act: -0.0001

Data Index: 259183 (C4 (Web Text))

Max Activating Token Index: 680

Text #7

Max Range: 0.8155. Min Range: -0.8155

Max Act: 0.6074. Min Act: -0.0001

Data Index: 751459 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 0.8155. Min Range: -0.8155

Max Act: 0.5994. Min Act: -0.0001

Data Index: 56613 (C4 (Web Text))

Max Activating Token Index: 1020

Text #9

Max Range: 0.8155. Min Range: -0.8155

Max Act: 0.5717. Min Act: -0.0001

Data Index: 933282 (C4 (Web Text))

Max Activating Token Index: 598

Text #10

Max Range: 0.8155. Min Range: -0.8155

Max Act: 0.5895. Min Act: -0.0001

Data Index: 772990 (C4 (Web Text))

Max Activating Token Index: 550

Text #11

Max Range: 0.8155. Min Range: -0.8155

Max Act: 0.5796. Min Act: -0.0001

Data Index: 867091 (C4 (Web Text))

Max Activating Token Index: 481

Text #12

Max Range: 0.8155. Min Range: -0.8155

Max Act: 0.5773. Min Act: -0.0001

Data Index: 559552 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 0.8155. Min Range: -0.8155

Max Act: 0.5572. Min Act: -0.0001

Data Index: 364124 (C4 (Web Text))

Max Activating Token Index: 966

Text #14

Max Range: 0.8155. Min Range: -0.8155

Max Act: 0.5742. Min Act: -0.0001

Data Index: 1049926 (C4 (Web Text))

Max Activating Token Index: 535

Text #15

Max Range: 0.8155. Min Range: -0.8155

Max Act: 0.5703. Min Act: -0.0001

Data Index: 931365 (C4 (Web Text))

Max Activating Token Index: 499

Text #16

Max Range: 0.8155. Min Range: -0.8155

Max Act: 0.5666. Min Act: -0.0001

Data Index: 862012 (C4 (Web Text))

Max Activating Token Index: 376

Text #17

Max Range: 0.8155. Min Range: -0.8155

Max Act: 0.5609. Min Act: -0.0001

Data Index: 1248995 (C4 (Web Text))

Max Activating Token Index: 912

Text #18

Max Range: 0.8155. Min Range: -0.8155

Max Act: 0.5614. Min Act: -0.0001

Data Index: 1089104 (C4 (Web Text))

Max Activating Token Index: 165

Text #19

Max Range: 0.8155. Min Range: -0.8155

Max Act: 0.5619. Min Act: -0.0001

Data Index: 981547 (C4 (Web Text))

Max Activating Token Index: 506