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

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

Neuron 128 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5230. Min Range: -1.5230

Max Act: 1.5230. Min Act: -0.0000

Data Index: 730938 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 1.5230. Min Range: -1.5230

Max Act: 1.4166. Min Act: -0.0000

Data Index: 459488 (C4 (Web Text))

Max Activating Token Index: 130

Text #2

Max Range: 1.5230. Min Range: -1.5230

Max Act: 1.2796. Min Act: -0.0000

Data Index: 241898 (C4 (Web Text))

Max Activating Token Index: 215

Text #3

Max Range: 1.5230. Min Range: -1.5230

Max Act: 1.2841. Min Act: -0.0000

Data Index: 516245 (C4 (Web Text))

Max Activating Token Index: 702

Text #4

Max Range: 1.5230. Min Range: -1.5230

Max Act: 1.2713. Min Act: -0.0000

Data Index: 739958 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 1.5230. Min Range: -1.5230

Max Act: 1.1395. Min Act: -0.0000

Data Index: 1002595 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 1.5230. Min Range: -1.5230

Max Act: 1.2050. Min Act: -0.0000

Data Index: 202889 (C4 (Web Text))

Max Activating Token Index: 561

Text #7

Max Range: 1.5230. Min Range: -1.5230

Max Act: 1.1382. Min Act: -0.0000

Data Index: 508844 (C4 (Web Text))

Max Activating Token Index: 319

Text #8

Max Range: 1.5230. Min Range: -1.5230

Max Act: 1.1901. Min Act: -0.0000

Data Index: 530263 (C4 (Web Text))

Max Activating Token Index: 613

Text #9

Max Range: 1.5230. Min Range: -1.5230

Max Act: 1.2736. Min Act: -0.0000

Data Index: 1200342 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 1.5230. Min Range: -1.5230

Max Act: 1.1494. Min Act: -0.0000

Data Index: 907042 (C4 (Web Text))

Max Activating Token Index: 591

Text #11

Max Range: 1.5230. Min Range: -1.5230

Max Act: 1.2033. Min Act: -0.0000

Data Index: 758136 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 1.5230. Min Range: -1.5230

Max Act: 1.1288. Min Act: -0.0000

Data Index: 63141 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 1.5230. Min Range: -1.5230

Max Act: 1.0620. Min Act: -0.0000

Data Index: 782490 (C4 (Web Text))

Max Activating Token Index: 610

Text #14

Max Range: 1.5230. Min Range: -1.5230

Max Act: 1.1850. Min Act: -0.0000

Data Index: 92827 (C4 (Web Text))

Max Activating Token Index: 279

Text #15

Max Range: 1.5230. Min Range: -1.5230

Max Act: 1.0501. Min Act: -0.0000

Data Index: 1099762 (C4 (Web Text))

Max Activating Token Index: 188

Text #16

Max Range: 1.5230. Min Range: -1.5230

Max Act: 1.1656. Min Act: -0.0000

Data Index: 66607 (C4 (Web Text))

Max Activating Token Index: 211

Text #17

Max Range: 1.5230. Min Range: -1.5230

Max Act: 1.1592. Min Act: -0.0000

Data Index: 855085 (C4 (Web Text))

Max Activating Token Index: 479

Text #18

Max Range: 1.5230. Min Range: -1.5230

Max Act: 1.1505. Min Act: -0.0000

Data Index: 724664 (C4 (Web Text))

Max Activating Token Index: 789

Text #19

Max Range: 1.5230. Min Range: -1.5230

Max Act: 1.0155. Min Act: -0.0000

Data Index: 459522 (C4 (Web Text))

Max Activating Token Index: 193