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

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

Neuron 866 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: 1.2493. Min Range: -1.2493

Max Act: 1.2493. Min Act: -0.0000

Data Index: 674229 (C4 (Web Text))

Max Activating Token Index: 852

Text #1

Max Range: 1.2493. Min Range: -1.2493

Max Act: 1.1616. Min Act: -0.0000

Data Index: 238468 (C4 (Web Text))

Max Activating Token Index: 250

Text #2

Max Range: 1.2493. Min Range: -1.2493

Max Act: 1.1281. Min Act: -0.0000

Data Index: 1522046 (Python Code)

Max Activating Token Index: 216

Text #3

Max Range: 1.2493. Min Range: -1.2493

Max Act: 0.9484. Min Act: -0.0000

Data Index: 428938 (C4 (Web Text))

Max Activating Token Index: 254

Text #4

Max Range: 1.2493. Min Range: -1.2493

Max Act: 0.9010. Min Act: -0.0000

Data Index: 393717 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 1.2493. Min Range: -1.2493

Max Act: 0.8376. Min Act: -0.0000

Data Index: 1518395 (Python Code)

Max Activating Token Index: 676

Text #6

Max Range: 1.2493. Min Range: -1.2493

Max Act: 1.0764. Min Act: -0.0000

Data Index: 716074 (C4 (Web Text))

Max Activating Token Index: 609

Text #7

Max Range: 1.2493. Min Range: -1.2493

Max Act: 1.0184. Min Act: -0.0000

Data Index: 441 (C4 (Web Text))

Max Activating Token Index: 742

Text #8

Max Range: 1.2493. Min Range: -1.2493

Max Act: 0.9663. Min Act: -0.0000

Data Index: 893709 (C4 (Web Text))

Max Activating Token Index: 729

Text #9

Max Range: 1.2493. Min Range: -1.2493

Max Act: 0.8355. Min Act: -0.0000

Data Index: 1125275 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 1.2493. Min Range: -1.2493

Max Act: 0.9506. Min Act: -0.0000

Data Index: 1460024 (Python Code)

Max Activating Token Index: 742

Text #11

Max Range: 1.2493. Min Range: -1.2493

Max Act: 0.9164. Min Act: -0.0000

Data Index: 311858 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 1.2493. Min Range: -1.2493

Max Act: 0.9177. Min Act: -0.0000

Data Index: 868971 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 1.2493. Min Range: -1.2493

Max Act: 0.8864. Min Act: -0.0000

Data Index: 1606090 (Python Code)

Max Activating Token Index: 532

Text #14

Max Range: 1.2493. Min Range: -1.2493

Max Act: 0.9081. Min Act: -0.0000

Data Index: 941323 (C4 (Web Text))

Max Activating Token Index: 349

Text #15

Max Range: 1.2493. Min Range: -1.2493

Max Act: 0.7953. Min Act: -0.0000

Data Index: 1601726 (Python Code)

Max Activating Token Index: 766

Text #16

Max Range: 1.2493. Min Range: -1.2493

Max Act: 0.9213. Min Act: -0.0000

Data Index: 1026535 (C4 (Web Text))

Max Activating Token Index: 239

Text #17

Max Range: 1.2493. Min Range: -1.2493

Max Act: 0.8871. Min Act: -0.0000

Data Index: 1006912 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 1.2493. Min Range: -1.2493

Max Act: 0.8583. Min Act: -0.0000

Data Index: 366535 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 1.2493. Min Range: -1.2493

Max Act: 0.7763. Min Act: -0.0000

Data Index: 839322 (C4 (Web Text))

Max Activating Token Index: 359