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

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

Neuron 3531 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6999. Min Range: -4.6999

Max Act: 4.6999. Min Act: -0.0002

Data Index: 1216590 (C4 (Web Text))

Max Activating Token Index: 793

Text #1

Max Range: 4.6999. Min Range: -4.6999

Max Act: 4.2883. Min Act: -0.0002

Data Index: 330057 (C4 (Web Text))

Max Activating Token Index: 481

Text #2

Max Range: 4.6999. Min Range: -4.6999

Max Act: 4.1829. Min Act: -0.0001

Data Index: 6520 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 4.6999. Min Range: -4.6999

Max Act: 4.0613. Min Act: -0.0002

Data Index: 523819 (C4 (Web Text))

Max Activating Token Index: 255

Text #4

Max Range: 4.6999. Min Range: -4.6999

Max Act: 3.9335. Min Act: -0.0002

Data Index: 1339596 (C4 (Web Text))

Max Activating Token Index: 725

Text #5

Max Range: 4.6999. Min Range: -4.6999

Max Act: 3.4015. Min Act: -0.0002

Data Index: 343821 (C4 (Web Text))

Max Activating Token Index: 467

Text #6

Max Range: 4.6999. Min Range: -4.6999

Max Act: 3.2530. Min Act: -0.0002

Data Index: 408092 (C4 (Web Text))

Max Activating Token Index: 594

Text #7

Max Range: 4.6999. Min Range: -4.6999

Max Act: 3.3441. Min Act: -0.0002

Data Index: 702365 (C4 (Web Text))

Max Activating Token Index: 871

Text #8

Max Range: 4.6999. Min Range: -4.6999

Max Act: 3.2416. Min Act: -0.0001

Data Index: 730606 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 4.6999. Min Range: -4.6999

Max Act: 3.4005. Min Act: -0.0002

Data Index: 1167814 (C4 (Web Text))

Max Activating Token Index: 511

Text #10

Max Range: 4.6999. Min Range: -4.6999

Max Act: 3.2549. Min Act: -0.0002

Data Index: 518419 (C4 (Web Text))

Max Activating Token Index: 940

Text #11

Max Range: 4.6999. Min Range: -4.6999

Max Act: 3.3016. Min Act: -0.0001

Data Index: 1340177 (C4 (Web Text))

Max Activating Token Index: 1012

Text #12

Max Range: 4.6999. Min Range: -4.6999

Max Act: 3.1649. Min Act: -0.0002

Data Index: 843413 (C4 (Web Text))

Max Activating Token Index: 588

Text #13

Max Range: 4.6999. Min Range: -4.6999

Max Act: 3.1566. Min Act: -0.0001

Data Index: 315565 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 4.6999. Min Range: -4.6999

Max Act: 3.0312. Min Act: -0.0001

Data Index: 1022414 (C4 (Web Text))

Max Activating Token Index: 522

Text #15

Max Range: 4.6999. Min Range: -4.6999

Max Act: 2.9710. Min Act: -0.0002

Data Index: 1257035 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 4.6999. Min Range: -4.6999

Max Act: 3.2514. Min Act: -0.0002

Data Index: 950576 (C4 (Web Text))

Max Activating Token Index: 684

Text #17

Max Range: 4.6999. Min Range: -4.6999

Max Act: 2.9880. Min Act: -0.0002

Data Index: 96432 (C4 (Web Text))

Max Activating Token Index: 714

Text #18

Max Range: 4.6999. Min Range: -4.6999

Max Act: 2.7263. Min Act: -0.0002

Data Index: 491158 (C4 (Web Text))

Max Activating Token Index: 919

Text #19

Max Range: 4.6999. Min Range: -4.6999

Max Act: 2.8821. Min Act: -0.0002

Data Index: 1262557 (C4 (Web Text))

Max Activating Token Index: 489