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

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

Neuron 2017 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: 0.7862. Min Range: -0.7862

Max Act: 0.7862. Min Act: -0.0001

Data Index: 1297835 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 0.7862. Min Range: -0.7862

Max Act: 0.7409. Min Act: -0.0001

Data Index: 1329333 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 0.7862. Min Range: -0.7862

Max Act: 0.6989. Min Act: -0.0001

Data Index: 944663 (C4 (Web Text))

Max Activating Token Index: 918

Text #3

Max Range: 0.7862. Min Range: -0.7862

Max Act: 0.7649. Min Act: -0.0001

Data Index: 730457 (C4 (Web Text))

Max Activating Token Index: 281

Text #4

Max Range: 0.7862. Min Range: -0.7862

Max Act: 0.7697. Min Act: -0.0001

Data Index: 444565 (C4 (Web Text))

Max Activating Token Index: 607

Text #5

Max Range: 0.7862. Min Range: -0.7862

Max Act: 0.7685. Min Act: -0.0001

Data Index: 1019135 (C4 (Web Text))

Max Activating Token Index: 491

Text #6

Max Range: 0.7862. Min Range: -0.7862

Max Act: 0.7661. Min Act: -0.0001

Data Index: 877443 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 0.7862. Min Range: -0.7862

Max Act: 0.6930. Min Act: -0.0001

Data Index: 1181185 (C4 (Web Text))

Max Activating Token Index: 501

Text #8

Max Range: 0.7862. Min Range: -0.7862

Max Act: 0.5860. Min Act: -0.0001

Data Index: 46407 (C4 (Web Text))

Max Activating Token Index: 704

Text #9

Max Range: 0.7862. Min Range: -0.7862

Max Act: 0.6880. Min Act: -0.0001

Data Index: 879738 (C4 (Web Text))

Max Activating Token Index: 744

Text #10

Max Range: 0.7862. Min Range: -0.7862

Max Act: 0.6867. Min Act: -0.0001

Data Index: 478236 (C4 (Web Text))

Max Activating Token Index: 396

Text #11

Max Range: 0.7862. Min Range: -0.7862

Max Act: 0.6365. Min Act: -0.0001

Data Index: 675655 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 0.7862. Min Range: -0.7862

Max Act: 0.6977. Min Act: -0.0001

Data Index: 858356 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 0.7862. Min Range: -0.7862

Max Act: 0.6175. Min Act: -0.0001

Data Index: 451131 (C4 (Web Text))

Max Activating Token Index: 506

Text #14

Max Range: 0.7862. Min Range: -0.7862

Max Act: 0.6801. Min Act: -0.0001

Data Index: 1779 (C4 (Web Text))

Max Activating Token Index: 29

Text #15

Max Range: 0.7862. Min Range: -0.7862

Max Act: 0.6319. Min Act: -0.0001

Data Index: 954822 (C4 (Web Text))

Max Activating Token Index: 648

Text #16

Max Range: 0.7862. Min Range: -0.7862

Max Act: 0.6491. Min Act: -0.0001

Data Index: 612871 (C4 (Web Text))

Max Activating Token Index: 248

Text #17

Max Range: 0.7862. Min Range: -0.7862

Max Act: 0.6403. Min Act: -0.0001

Data Index: 151313 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 0.7862. Min Range: -0.7862

Max Act: 0.6387. Min Act: -0.0001

Data Index: 1282960 (C4 (Web Text))

Max Activating Token Index: 815

Text #19

Max Range: 0.7862. Min Range: -0.7862

Max Act: 0.6388. Min Act: -0.0001

Data Index: 249726 (C4 (Web Text))

Max Activating Token Index: 411