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

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

Neuron 658 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: 0.0735. Min Range: -0.0735

Max Act: 0.0735. Min Act: -0.0005

Data Index: 597292 (C4 (Web Text))

Max Activating Token Index: 368

Text #1

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0610. Min Act: -0.0005

Data Index: 1050109 (C4 (Web Text))

Max Activating Token Index: 439

Text #2

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0593. Min Act: -0.0005

Data Index: 43552 (C4 (Web Text))

Max Activating Token Index: 820

Text #3

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0553. Min Act: -0.0005

Data Index: 342359 (C4 (Web Text))

Max Activating Token Index: 397

Text #4

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0542. Min Act: -0.0005

Data Index: 254516 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0524. Min Act: -0.0005

Data Index: 377150 (C4 (Web Text))

Max Activating Token Index: 552

Text #6

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0520. Min Act: -0.0005

Data Index: 1094798 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0524. Min Act: -0.0005

Data Index: 103882 (C4 (Web Text))

Max Activating Token Index: 397

Text #8

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0527. Min Act: -0.0005

Data Index: 196253 (C4 (Web Text))

Max Activating Token Index: 936

Text #9

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0504. Min Act: -0.0005

Data Index: 1085810 (C4 (Web Text))

Max Activating Token Index: 573

Text #10

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0510. Min Act: -0.0005

Data Index: 921908 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0502. Min Act: -0.0005

Data Index: 992121 (C4 (Web Text))

Max Activating Token Index: 791

Text #12

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0502. Min Act: -0.0005

Data Index: 552529 (C4 (Web Text))

Max Activating Token Index: 578

Text #13

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0501. Min Act: -0.0005

Data Index: 799707 (C4 (Web Text))

Max Activating Token Index: 809

Text #14

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0498. Min Act: -0.0005

Data Index: 830933 (C4 (Web Text))

Max Activating Token Index: 906

Text #15

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0497. Min Act: -0.0005

Data Index: 1154852 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0484. Min Act: -0.0005

Data Index: 167786 (C4 (Web Text))

Max Activating Token Index: 940

Text #17

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0494. Min Act: -0.0004

Data Index: 596154 (C4 (Web Text))

Max Activating Token Index: 542

Text #18

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0500. Min Act: -0.0005

Data Index: 488178 (C4 (Web Text))

Max Activating Token Index: 345

Text #19

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0487. Min Act: -0.0005

Data Index: 166369 (C4 (Web Text))

Max Activating Token Index: 119