Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 818 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4626. Min Range: -0.4626

Max Act: 0.4626. Min Act: -0.0000

Data Index: 789113 (C4 (Web Text))

Max Activating Token Index: 265

Text #1

Max Range: 0.4626. Min Range: -0.4626

Max Act: 0.3848. Min Act: -0.0000

Data Index: 852961 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 0.4626. Min Range: -0.4626

Max Act: 0.3796. Min Act: -0.0000

Data Index: 685790 (C4 (Web Text))

Max Activating Token Index: 317

Text #3

Max Range: 0.4626. Min Range: -0.4626

Max Act: 0.3623. Min Act: -0.0000

Data Index: 239542 (C4 (Web Text))

Max Activating Token Index: 701

Text #4

Max Range: 0.4626. Min Range: -0.4626

Max Act: 0.3540. Min Act: -0.0000

Data Index: 713881 (C4 (Web Text))

Max Activating Token Index: 737

Text #5

Max Range: 0.4626. Min Range: -0.4626

Max Act: 0.3513. Min Act: -0.0000

Data Index: 207603 (C4 (Web Text))

Max Activating Token Index: 553

Text #6

Max Range: 0.4626. Min Range: -0.4626

Max Act: 0.3631. Min Act: -0.0000

Data Index: 757592 (C4 (Web Text))

Max Activating Token Index: 885

Text #7

Max Range: 0.4626. Min Range: -0.4626

Max Act: 0.3416. Min Act: -0.0000

Data Index: 667493 (C4 (Web Text))

Max Activating Token Index: 812

Text #8

Max Range: 0.4626. Min Range: -0.4626

Max Act: 0.3270. Min Act: -0.0000

Data Index: 793577 (C4 (Web Text))

Max Activating Token Index: 996

Text #9

Max Range: 0.4626. Min Range: -0.4626

Max Act: 0.3335. Min Act: -0.0000

Data Index: 905740 (C4 (Web Text))

Max Activating Token Index: 366

Text #10

Max Range: 0.4626. Min Range: -0.4626

Max Act: 0.3178. Min Act: -0.0000

Data Index: 825499 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 0.4626. Min Range: -0.4626

Max Act: 0.3106. Min Act: -0.0000

Data Index: 418903 (C4 (Web Text))

Max Activating Token Index: 437

Text #12

Max Range: 0.4626. Min Range: -0.4626

Max Act: 0.2989. Min Act: -0.0000

Data Index: 683391 (C4 (Web Text))

Max Activating Token Index: 328

Text #13

Max Range: 0.4626. Min Range: -0.4626

Max Act: 0.3468. Min Act: -0.0000

Data Index: 494120 (C4 (Web Text))

Max Activating Token Index: 900

Text #14

Max Range: 0.4626. Min Range: -0.4626

Max Act: 0.3169. Min Act: -0.0000

Data Index: 338265 (C4 (Web Text))

Max Activating Token Index: 36

Text #15

Max Range: 0.4626. Min Range: -0.4626

Max Act: 0.3038. Min Act: -0.0000

Data Index: 1215918 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 0.4626. Min Range: -0.4626

Max Act: 0.2922. Min Act: -0.0000

Data Index: 663201 (C4 (Web Text))

Max Activating Token Index: 118

Text #17

Max Range: 0.4626. Min Range: -0.4626

Max Act: 0.3008. Min Act: -0.0000

Data Index: 383752 (C4 (Web Text))

Max Activating Token Index: 353

Text #18

Max Range: 0.4626. Min Range: -0.4626

Max Act: 0.2992. Min Act: -0.0000

Data Index: 464763 (C4 (Web Text))

Max Activating Token Index: 394

Text #19

Max Range: 0.4626. Min Range: -0.4626

Max Act: 0.2972. Min Act: -0.0000

Data Index: 102676 (C4 (Web Text))

Max Activating Token Index: 365