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

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

Neuron 877 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9963. Min Range: -1.9963

Max Act: 1.9963. Min Act: -0.0000

Data Index: 1249357 (C4 (Web Text))

Max Activating Token Index: 895

Text #1

Max Range: 1.9963. Min Range: -1.9963

Max Act: 1.8234. Min Act: -0.0000

Data Index: 1590392 (Python Code)

Max Activating Token Index: 173

Text #2

Max Range: 1.9963. Min Range: -1.9963

Max Act: 1.6515. Min Act: -0.0000

Data Index: 203952 (C4 (Web Text))

Max Activating Token Index: 154

Text #3

Max Range: 1.9963. Min Range: -1.9963

Max Act: 1.7374. Min Act: -0.0000

Data Index: 1118328 (C4 (Web Text))

Max Activating Token Index: 886

Text #4

Max Range: 1.9963. Min Range: -1.9963

Max Act: 1.6704. Min Act: -0.0000

Data Index: 429682 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 1.9963. Min Range: -1.9963

Max Act: 1.6162. Min Act: -0.0000

Data Index: 549354 (C4 (Web Text))

Max Activating Token Index: 561

Text #6

Max Range: 1.9963. Min Range: -1.9963

Max Act: 1.5885. Min Act: -0.0000

Data Index: 1218232 (C4 (Web Text))

Max Activating Token Index: 462

Text #7

Max Range: 1.9963. Min Range: -1.9963

Max Act: 1.5396. Min Act: -0.0000

Data Index: 387318 (C4 (Web Text))

Max Activating Token Index: 358

Text #8

Max Range: 1.9963. Min Range: -1.9963

Max Act: 1.6293. Min Act: -0.0000

Data Index: 778165 (C4 (Web Text))

Max Activating Token Index: 627

Text #9

Max Range: 1.9963. Min Range: -1.9963

Max Act: 1.6296. Min Act: -0.0000

Data Index: 1624998 (Python Code)

Max Activating Token Index: 30

Text #10

Max Range: 1.9963. Min Range: -1.9963

Max Act: 1.6237. Min Act: -0.0000

Data Index: 730202 (C4 (Web Text))

Max Activating Token Index: 559

Text #11

Max Range: 1.9963. Min Range: -1.9963

Max Act: 1.5082. Min Act: -0.0000

Data Index: 1501946 (Python Code)

Max Activating Token Index: 154

Text #12

Max Range: 1.9963. Min Range: -1.9963

Max Act: 1.5044. Min Act: -0.0000

Data Index: 553625 (C4 (Web Text))

Max Activating Token Index: 41

Text #13

Max Range: 1.9963. Min Range: -1.9963

Max Act: 1.5325. Min Act: -0.0000

Data Index: 56443 (C4 (Web Text))

Max Activating Token Index: 715

Text #14

Max Range: 1.9963. Min Range: -1.9963

Max Act: 1.2786. Min Act: -0.0000

Data Index: 307297 (C4 (Web Text))

Max Activating Token Index: 307

Text #15

Max Range: 1.9963. Min Range: -1.9963

Max Act: 1.4287. Min Act: -0.0000

Data Index: 648316 (C4 (Web Text))

Max Activating Token Index: 893

Text #16

Max Range: 1.9963. Min Range: -1.9963

Max Act: 1.4201. Min Act: -0.0000

Data Index: 558659 (C4 (Web Text))

Max Activating Token Index: 466

Text #17

Max Range: 1.9963. Min Range: -1.9963

Max Act: 1.3830. Min Act: -0.0000

Data Index: 865041 (C4 (Web Text))

Max Activating Token Index: 603

Text #18

Max Range: 1.9963. Min Range: -1.9963

Max Act: 1.3796. Min Act: -0.0000

Data Index: 941057 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 1.9963. Min Range: -1.9963

Max Act: 1.3664. Min Act: -0.0000

Data Index: 1381560 (Python Code)

Max Activating Token Index: 101