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

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

Neuron 2040 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: 0.0513. Min Range: -0.0513

Max Act: 0.0502. Min Act: -0.0003

Data Index: 541443 (C4 (Web Text))

Max Activating Token Index: 370

Text #1

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0513. Min Act: -0.0003

Data Index: 97843 (C4 (Web Text))

Max Activating Token Index: 727

Text #2

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0443. Min Act: -0.0003

Data Index: 770390 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0448. Min Act: -0.0003

Data Index: 1099485 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0436. Min Act: -0.0003

Data Index: 1333387 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0426. Min Act: -0.0003

Data Index: 1074085 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0426. Min Act: -0.0004

Data Index: 775803 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0419. Min Act: -0.0003

Data Index: 645433 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0412. Min Act: -0.0003

Data Index: 242782 (C4 (Web Text))

Max Activating Token Index: 810

Text #9

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0417. Min Act: -0.0003

Data Index: 1124564 (C4 (Web Text))

Max Activating Token Index: 132

Text #10

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0405. Min Act: -0.0003

Data Index: 734118 (C4 (Web Text))

Max Activating Token Index: 123

Text #11

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0417. Min Act: -0.0003

Data Index: 517159 (C4 (Web Text))

Max Activating Token Index: 1012

Text #12

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0412. Min Act: -0.0001

Data Index: 578502 (C4 (Web Text))

Max Activating Token Index: 120

Text #13

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0412. Min Act: -0.0003

Data Index: 726320 (C4 (Web Text))

Max Activating Token Index: 236

Text #14

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0404. Min Act: -0.0003

Data Index: 1195820 (C4 (Web Text))

Max Activating Token Index: 620

Text #15

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0408. Min Act: -0.0004

Data Index: 1350622 (C4 (Web Text))

Max Activating Token Index: 560

Text #16

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0403. Min Act: -0.0003

Data Index: 1074011 (C4 (Web Text))

Max Activating Token Index: 730

Text #17

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0406. Min Act: -0.0002

Data Index: 993806 (C4 (Web Text))

Max Activating Token Index: 274

Text #18

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0390. Min Act: -0.0003

Data Index: 807554 (C4 (Web Text))

Max Activating Token Index: 1008

Text #19

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0397. Min Act: -0.0003

Data Index: 1106253 (C4 (Web Text))

Max Activating Token Index: 523