Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3984 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3923. Min Range: -1.3923

Max Act: 1.3923. Min Act: -0.0000

Data Index: 877410 (C4 (Web Text))

Max Activating Token Index: 603

Text #1

Max Range: 1.3923. Min Range: -1.3923

Max Act: 1.2088. Min Act: -0.0000

Data Index: 992962 (C4 (Web Text))

Max Activating Token Index: 933

Text #2

Max Range: 1.3923. Min Range: -1.3923

Max Act: 1.2721. Min Act: -0.0000

Data Index: 1300399 (C4 (Web Text))

Max Activating Token Index: 347

Text #3

Max Range: 1.3923. Min Range: -1.3923

Max Act: 1.1072. Min Act: -0.0000

Data Index: 561742 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 1.3923. Min Range: -1.3923

Max Act: 0.8291. Min Act: -0.0000

Data Index: 210911 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 1.3923. Min Range: -1.3923

Max Act: 0.8205. Min Act: -0.0000

Data Index: 572818 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 1.3923. Min Range: -1.3923

Max Act: 0.7912. Min Act: -0.0000

Data Index: 371157 (C4 (Web Text))

Max Activating Token Index: 248

Text #7

Max Range: 1.3923. Min Range: -1.3923

Max Act: 0.7613. Min Act: -0.0000

Data Index: 261774 (C4 (Web Text))

Max Activating Token Index: 731

Text #8

Max Range: 1.3923. Min Range: -1.3923

Max Act: 0.8499. Min Act: -0.0000

Data Index: 206686 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 1.3923. Min Range: -1.3923

Max Act: 0.7103. Min Act: -0.0000

Data Index: 1122583 (C4 (Web Text))

Max Activating Token Index: 272

Text #10

Max Range: 1.3923. Min Range: -1.3923

Max Act: 0.7674. Min Act: -0.0000

Data Index: 563363 (C4 (Web Text))

Max Activating Token Index: 229

Text #11

Max Range: 1.3923. Min Range: -1.3923

Max Act: 0.6615. Min Act: -0.0000

Data Index: 717126 (C4 (Web Text))

Max Activating Token Index: 651

Text #12

Max Range: 1.3923. Min Range: -1.3923

Max Act: 0.6306. Min Act: -0.0000

Data Index: 150239 (C4 (Web Text))

Max Activating Token Index: 211

Text #13

Max Range: 1.3923. Min Range: -1.3923

Max Act: 0.7264. Min Act: -0.0000

Data Index: 110443 (C4 (Web Text))

Max Activating Token Index: 728

Text #14

Max Range: 1.3923. Min Range: -1.3923

Max Act: 0.6662. Min Act: -0.0000

Data Index: 432802 (C4 (Web Text))

Max Activating Token Index: 430

Text #15

Max Range: 1.3923. Min Range: -1.3923

Max Act: 0.6231. Min Act: -0.0000

Data Index: 1617625 (Python Code)

Max Activating Token Index: 421

Text #16

Max Range: 1.3923. Min Range: -1.3923

Max Act: 0.6337. Min Act: -0.0000

Data Index: 884494 (C4 (Web Text))

Max Activating Token Index: 762

Text #17

Max Range: 1.3923. Min Range: -1.3923

Max Act: 0.5681. Min Act: -0.0000

Data Index: 844306 (C4 (Web Text))

Max Activating Token Index: 824

Text #18

Max Range: 1.3923. Min Range: -1.3923

Max Act: 0.6372. Min Act: -0.0000

Data Index: 722637 (C4 (Web Text))

Max Activating Token Index: 656

Text #19

Max Range: 1.3923. Min Range: -1.3923

Max Act: 0.6083. Min Act: -0.0000

Data Index: 256933 (C4 (Web Text))

Max Activating Token Index: 117