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

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

Neuron 2122 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0716. Min Act: -0.0003

Data Index: 1016059 (C4 (Web Text))

Max Activating Token Index: 511

Text #1

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0737. Min Act: -0.0003

Data Index: 1240710 (C4 (Web Text))

Max Activating Token Index: 463

Text #2

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0720. Min Act: -0.0003

Data Index: 1204032 (C4 (Web Text))

Max Activating Token Index: 407

Text #3

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0702. Min Act: -0.0003

Data Index: 20096 (C4 (Web Text))

Max Activating Token Index: 446

Text #4

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0673. Min Act: -0.0003

Data Index: 147295 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0667. Min Act: -0.0003

Data Index: 107577 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0617. Min Act: -0.0003

Data Index: 1134600 (C4 (Web Text))

Max Activating Token Index: 975

Text #7

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0652. Min Act: -0.0003

Data Index: 102116 (C4 (Web Text))

Max Activating Token Index: 247

Text #8

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0600. Min Act: -0.0003

Data Index: 1355753 (C4 (Web Text))

Max Activating Token Index: 353

Text #9

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0637. Min Act: -0.0003

Data Index: 727339 (C4 (Web Text))

Max Activating Token Index: 187

Text #10

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0564. Min Act: -0.0003

Data Index: 407886 (C4 (Web Text))

Max Activating Token Index: 879

Text #11

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0547. Min Act: -0.0003

Data Index: 956903 (C4 (Web Text))

Max Activating Token Index: 490

Text #12

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0572. Min Act: -0.0003

Data Index: 92091 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0572. Min Act: -0.0003

Data Index: 185340 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0536. Min Act: -0.0003

Data Index: 754766 (C4 (Web Text))

Max Activating Token Index: 71

Text #15

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0579. Min Act: -0.0003

Data Index: 73742 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0515. Min Act: -0.0003

Data Index: 600983 (C4 (Web Text))

Max Activating Token Index: 299

Text #17

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0570. Min Act: -0.0003

Data Index: 1089375 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0594. Min Act: -0.0003

Data Index: 772014 (C4 (Web Text))

Max Activating Token Index: 1016

Text #19

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0585. Min Act: -0.0003

Data Index: 265752 (C4 (Web Text))

Max Activating Token Index: 930