Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 912 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0678. Min Act: -0.0005

Data Index: 1254720 (C4 (Web Text))

Max Activating Token Index: 683

Text #1

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0657. Min Act: -0.0005

Data Index: 167644 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0586. Min Act: -0.0005

Data Index: 581379 (C4 (Web Text))

Max Activating Token Index: 679

Text #3

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0575. Min Act: -0.0005

Data Index: 506350 (C4 (Web Text))

Max Activating Token Index: 365

Text #4

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0597. Min Act: -0.0005

Data Index: 1171648 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0590. Min Act: -0.0005

Data Index: 161141 (C4 (Web Text))

Max Activating Token Index: 835

Text #6

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0574. Min Act: -0.0005

Data Index: 1277401 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0564. Min Act: -0.0005

Data Index: 1154270 (C4 (Web Text))

Max Activating Token Index: 642

Text #8

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0578. Min Act: -0.0005

Data Index: 865663 (C4 (Web Text))

Max Activating Token Index: 790

Text #9

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0561. Min Act: -0.0005

Data Index: 1020391 (C4 (Web Text))

Max Activating Token Index: 172

Text #10

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0571. Min Act: -0.0005

Data Index: 1328615 (C4 (Web Text))

Max Activating Token Index: 432

Text #11

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0541. Min Act: -0.0005

Data Index: 632345 (C4 (Web Text))

Max Activating Token Index: 371

Text #12

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0559. Min Act: -0.0005

Data Index: 222182 (C4 (Web Text))

Max Activating Token Index: 412

Text #13

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0561. Min Act: -0.0005

Data Index: 73235 (C4 (Web Text))

Max Activating Token Index: 103

Text #14

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0557. Min Act: -0.0005

Data Index: 126301 (C4 (Web Text))

Max Activating Token Index: 97

Text #15

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0547. Min Act: -0.0005

Data Index: 151900 (C4 (Web Text))

Max Activating Token Index: 367

Text #16

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0546. Min Act: -0.0005

Data Index: 913854 (C4 (Web Text))

Max Activating Token Index: 617

Text #17

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0530. Min Act: -0.0005

Data Index: 649450 (C4 (Web Text))

Max Activating Token Index: 464

Text #18

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0541. Min Act: -0.0005

Data Index: 539748 (C4 (Web Text))

Max Activating Token Index: 135

Text #19

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0570. Min Act: -0.0005

Data Index: 862410 (C4 (Web Text))

Max Activating Token Index: 577