Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 394 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0689. Min Act: -0.0003

Data Index: 1264558 (C4 (Web Text))

Max Activating Token Index: 690

Text #1

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0631. Min Act: -0.0002

Data Index: 257237 (C4 (Web Text))

Max Activating Token Index: 287

Text #2

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0565. Min Act: -0.0003

Data Index: 1039846 (C4 (Web Text))

Max Activating Token Index: 467

Text #3

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0517. Min Act: -0.0003

Data Index: 1103424 (C4 (Web Text))

Max Activating Token Index: 883

Text #4

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0502. Min Act: -0.0003

Data Index: 686660 (C4 (Web Text))

Max Activating Token Index: 315

Text #5

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0502. Min Act: -0.0003

Data Index: 87215 (C4 (Web Text))

Max Activating Token Index: 122

Text #6

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0487. Min Act: -0.0003

Data Index: 895373 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0499. Min Act: -0.0003

Data Index: 1193159 (C4 (Web Text))

Max Activating Token Index: 534

Text #8

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0489. Min Act: -0.0003

Data Index: 310886 (C4 (Web Text))

Max Activating Token Index: 247

Text #9

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0490. Min Act: -0.0003

Data Index: 1002723 (C4 (Web Text))

Max Activating Token Index: 179

Text #10

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0491. Min Act: -0.0004

Data Index: 433249 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0498. Min Act: -0.0003

Data Index: 330483 (C4 (Web Text))

Max Activating Token Index: 465

Text #12

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0495. Min Act: -0.0003

Data Index: 1319629 (C4 (Web Text))

Max Activating Token Index: 502

Text #13

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0500. Min Act: -0.0003

Data Index: 1252258 (C4 (Web Text))

Max Activating Token Index: 268

Text #14

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0491. Min Act: -0.0003

Data Index: 1357838 (C4 (Web Text))

Max Activating Token Index: 281

Text #15

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0487. Min Act: -0.0003

Data Index: 495816 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0475. Min Act: -0.0003

Data Index: 160872 (C4 (Web Text))

Max Activating Token Index: 776

Text #17

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0475. Min Act: -0.0003

Data Index: 453546 (C4 (Web Text))

Max Activating Token Index: 82

Text #18

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0466. Min Act: -0.0003

Data Index: 443352 (C4 (Web Text))

Max Activating Token Index: 881

Text #19

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0457. Min Act: -0.0003

Data Index: 92664 (C4 (Web Text))

Max Activating Token Index: 879