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

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

Neuron 4880 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1480. Min Range: -3.1480

Max Act: 3.1480. Min Act: -0.0000

Data Index: 167417 (C4 (Web Text))

Max Activating Token Index: 403

Text #1

Max Range: 3.1480. Min Range: -3.1480

Max Act: 2.6231. Min Act: -0.0001

Data Index: 1355680 (C4 (Web Text))

Max Activating Token Index: 209

Text #2

Max Range: 3.1480. Min Range: -3.1480

Max Act: 2.5915. Min Act: -0.0000

Data Index: 1250839 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 3.1480. Min Range: -3.1480

Max Act: 2.3316. Min Act: -0.0000

Data Index: 1096554 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 3.1480. Min Range: -3.1480

Max Act: 2.5060. Min Act: -0.0000

Data Index: 431386 (C4 (Web Text))

Max Activating Token Index: 99

Text #5

Max Range: 3.1480. Min Range: -3.1480

Max Act: 2.4283. Min Act: -0.0000

Data Index: 264739 (C4 (Web Text))

Max Activating Token Index: 277

Text #6

Max Range: 3.1480. Min Range: -3.1480

Max Act: 2.1051. Min Act: -0.0000

Data Index: 356881 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 3.1480. Min Range: -3.1480

Max Act: 1.9800. Min Act: -0.0000

Data Index: 640966 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 3.1480. Min Range: -3.1480

Max Act: 2.0821. Min Act: -0.0000

Data Index: 860970 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 3.1480. Min Range: -3.1480

Max Act: 1.9723. Min Act: -0.0000

Data Index: 996004 (C4 (Web Text))

Max Activating Token Index: 364

Text #10

Max Range: 3.1480. Min Range: -3.1480

Max Act: 2.1204. Min Act: -0.0000

Data Index: 1277890 (C4 (Web Text))

Max Activating Token Index: 115

Text #11

Max Range: 3.1480. Min Range: -3.1480

Max Act: 2.0039. Min Act: -0.0000

Data Index: 487002 (C4 (Web Text))

Max Activating Token Index: 473

Text #12

Max Range: 3.1480. Min Range: -3.1480

Max Act: 2.1031. Min Act: -0.0000

Data Index: 888564 (C4 (Web Text))

Max Activating Token Index: 833

Text #13

Max Range: 3.1480. Min Range: -3.1480

Max Act: 1.9248. Min Act: -0.0000

Data Index: 1128516 (C4 (Web Text))

Max Activating Token Index: 966

Text #14

Max Range: 3.1480. Min Range: -3.1480

Max Act: 2.0689. Min Act: -0.0000

Data Index: 168666 (C4 (Web Text))

Max Activating Token Index: 933

Text #15

Max Range: 3.1480. Min Range: -3.1480

Max Act: 1.7644. Min Act: -0.0000

Data Index: 113792 (C4 (Web Text))

Max Activating Token Index: 508

Text #16

Max Range: 3.1480. Min Range: -3.1480

Max Act: 1.8520. Min Act: -0.0000

Data Index: 610142 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 3.1480. Min Range: -3.1480

Max Act: 1.8784. Min Act: -0.0000

Data Index: 47773 (C4 (Web Text))

Max Activating Token Index: 174

Text #18

Max Range: 3.1480. Min Range: -3.1480

Max Act: 1.7289. Min Act: -0.0000

Data Index: 436160 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 3.1480. Min Range: -3.1480

Max Act: 1.7564. Min Act: -0.0000

Data Index: 1181883 (C4 (Web Text))

Max Activating Token Index: 1010