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

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

Neuron 1221 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.8694. Min Act: -0.0001

Data Index: 34499 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.8903. Min Act: -0.0001

Data Index: 991875 (C4 (Web Text))

Max Activating Token Index: 734

Text #2

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.8624. Min Act: -0.0001

Data Index: 1205561 (C4 (Web Text))

Max Activating Token Index: 266

Text #3

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.8052. Min Act: -0.0001

Data Index: 352045 (C4 (Web Text))

Max Activating Token Index: 622

Text #4

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.7773. Min Act: -0.0001

Data Index: 440630 (C4 (Web Text))

Max Activating Token Index: 617

Text #5

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.7291. Min Act: -0.0001

Data Index: 1188892 (C4 (Web Text))

Max Activating Token Index: 277

Text #6

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.8136. Min Act: -0.0001

Data Index: 1086029 (C4 (Web Text))

Max Activating Token Index: 981

Text #7

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.7581. Min Act: -0.0001

Data Index: 821211 (C4 (Web Text))

Max Activating Token Index: 709

Text #8

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.7991. Min Act: -0.0001

Data Index: 1209319 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.7659. Min Act: -0.0001

Data Index: 1268443 (C4 (Web Text))

Max Activating Token Index: 386

Text #10

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.7382. Min Act: -0.0001

Data Index: 652361 (C4 (Web Text))

Max Activating Token Index: 226

Text #11

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.7229. Min Act: -0.0001

Data Index: 154706 (C4 (Web Text))

Max Activating Token Index: 422

Text #12

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.7596. Min Act: -0.0001

Data Index: 493625 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.6805. Min Act: -0.0001

Data Index: 984970 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.6795. Min Act: -0.0001

Data Index: 1049046 (C4 (Web Text))

Max Activating Token Index: 557

Text #15

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.6696. Min Act: -0.0001

Data Index: 539236 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.7073. Min Act: -0.0001

Data Index: 392871 (C4 (Web Text))

Max Activating Token Index: 783

Text #17

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.6838. Min Act: -0.0001

Data Index: 311106 (C4 (Web Text))

Max Activating Token Index: 341

Text #18

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.6006. Min Act: -0.0001

Data Index: 825229 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.6640. Min Act: -0.0001

Data Index: 356514 (C4 (Web Text))

Max Activating Token Index: 647