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

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

Neuron 700 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0033. Min Act: -0.0003

Data Index: 1596418 (Python Code)

Max Activating Token Index: 78

Text #1

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0031. Min Act: -0.0003

Data Index: 344341 (C4 (Web Text))

Max Activating Token Index: 655

Text #2

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0031. Min Act: -0.0003

Data Index: 519229 (C4 (Web Text))

Max Activating Token Index: 154

Text #3

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0033. Min Act: -0.0003

Data Index: 991160 (C4 (Web Text))

Max Activating Token Index: 594

Text #4

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0030. Min Act: -0.0003

Data Index: 1225192 (C4 (Web Text))

Max Activating Token Index: 96

Text #5

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0026. Min Act: -0.0003

Data Index: 1447209 (Python Code)

Max Activating Token Index: 666

Text #6

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0030. Min Act: -0.0003

Data Index: 629155 (C4 (Web Text))

Max Activating Token Index: 493

Text #7

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0028. Min Act: -0.0003

Data Index: 615445 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0030. Min Act: -0.0003

Data Index: 552626 (C4 (Web Text))

Max Activating Token Index: 450

Text #9

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0028. Min Act: -0.0003

Data Index: 913240 (C4 (Web Text))

Max Activating Token Index: 285

Text #10

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0028. Min Act: -0.0003

Data Index: 479024 (C4 (Web Text))

Max Activating Token Index: 298

Text #11

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0028. Min Act: -0.0003

Data Index: 1199643 (C4 (Web Text))

Max Activating Token Index: 101

Text #12

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0026. Min Act: -0.0003

Data Index: 1546808 (Python Code)

Max Activating Token Index: 795

Text #13

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0026. Min Act: -0.0003

Data Index: 828560 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0029. Min Act: -0.0003

Data Index: 1322593 (C4 (Web Text))

Max Activating Token Index: 232

Text #15

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0028. Min Act: -0.0003

Data Index: 733423 (C4 (Web Text))

Max Activating Token Index: 643

Text #16

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0028. Min Act: -0.0004

Data Index: 1253695 (C4 (Web Text))

Max Activating Token Index: 706

Text #17

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0028. Min Act: -0.0003

Data Index: 1629597 (Python Code)

Max Activating Token Index: 986

Text #18

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0031. Min Act: -0.0003

Data Index: 424641 (C4 (Web Text))

Max Activating Token Index: 649

Text #19

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0027. Min Act: -0.0003

Data Index: 905798 (C4 (Web Text))

Max Activating Token Index: 999