Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 889 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.4000. Min Act: -0.0004

Data Index: 909658 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.3832. Min Act: -0.0005

Data Index: 759669 (C4 (Web Text))

Max Activating Token Index: 334

Text #2

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.3926. Min Act: -0.0004

Data Index: 670093 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.3748. Min Act: -0.0004

Data Index: 1093393 (C4 (Web Text))

Max Activating Token Index: 971

Text #4

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.3741. Min Act: -0.0004

Data Index: 710541 (C4 (Web Text))

Max Activating Token Index: 142

Text #5

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.3642. Min Act: -0.0004

Data Index: 519506 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.3619. Min Act: -0.0004

Data Index: 1015895 (C4 (Web Text))

Max Activating Token Index: 988

Text #7

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.3568. Min Act: -0.0004

Data Index: 1300752 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.3547. Min Act: -0.0004

Data Index: 567448 (C4 (Web Text))

Max Activating Token Index: 774

Text #9

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.3402. Min Act: -0.0004

Data Index: 859134 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.3494. Min Act: -0.0004

Data Index: 562023 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.3491. Min Act: -0.0004

Data Index: 1358208 (C4 (Web Text))

Max Activating Token Index: 329

Text #12

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.3487. Min Act: -0.0004

Data Index: 954086 (C4 (Web Text))

Max Activating Token Index: 144

Text #13

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.3360. Min Act: -0.0004

Data Index: 1040273 (C4 (Web Text))

Max Activating Token Index: 617

Text #14

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.3472. Min Act: -0.0005

Data Index: 4206 (C4 (Web Text))

Max Activating Token Index: 149

Text #15

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.3471. Min Act: -0.0004

Data Index: 5944 (C4 (Web Text))

Max Activating Token Index: 996

Text #16

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.3465. Min Act: -0.0005

Data Index: 1020113 (C4 (Web Text))

Max Activating Token Index: 419

Text #17

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.3351. Min Act: -0.0004

Data Index: 604035 (C4 (Web Text))

Max Activating Token Index: 727

Text #18

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.3415. Min Act: -0.0004

Data Index: 408092 (C4 (Web Text))

Max Activating Token Index: 432

Text #19

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.3317. Min Act: -0.0005

Data Index: 325217 (C4 (Web Text))

Max Activating Token Index: 41