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

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

Neuron 3576 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2265. Min Range: -2.2265

Max Act: 2.0124. Min Act: -0.0000

Data Index: 1040429 (C4 (Web Text))

Max Activating Token Index: 779

Text #1

Max Range: 2.2265. Min Range: -2.2265

Max Act: 2.2265. Min Act: -0.0000

Data Index: 257442 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 2.2265. Min Range: -2.2265

Max Act: 1.9457. Min Act: -0.0000

Data Index: 1045751 (C4 (Web Text))

Max Activating Token Index: 715

Text #3

Max Range: 2.2265. Min Range: -2.2265

Max Act: 1.9667. Min Act: -0.0000

Data Index: 1116971 (C4 (Web Text))

Max Activating Token Index: 721

Text #4

Max Range: 2.2265. Min Range: -2.2265

Max Act: 1.8816. Min Act: -0.0000

Data Index: 1001740 (C4 (Web Text))

Max Activating Token Index: 536

Text #5

Max Range: 2.2265. Min Range: -2.2265

Max Act: 1.8568. Min Act: -0.0000

Data Index: 837262 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 2.2265. Min Range: -2.2265

Max Act: 1.8393. Min Act: -0.0000

Data Index: 109439 (C4 (Web Text))

Max Activating Token Index: 421

Text #7

Max Range: 2.2265. Min Range: -2.2265

Max Act: 1.9038. Min Act: -0.0000

Data Index: 170667 (C4 (Web Text))

Max Activating Token Index: 992

Text #8

Max Range: 2.2265. Min Range: -2.2265

Max Act: 1.7782. Min Act: -0.0000

Data Index: 97768 (C4 (Web Text))

Max Activating Token Index: 550

Text #9

Max Range: 2.2265. Min Range: -2.2265

Max Act: 1.8513. Min Act: -0.0000

Data Index: 1154905 (C4 (Web Text))

Max Activating Token Index: 933

Text #10

Max Range: 2.2265. Min Range: -2.2265

Max Act: 1.7367. Min Act: -0.0000

Data Index: 1291655 (C4 (Web Text))

Max Activating Token Index: 399

Text #11

Max Range: 2.2265. Min Range: -2.2265

Max Act: 1.7188. Min Act: -0.0000

Data Index: 347532 (C4 (Web Text))

Max Activating Token Index: 701

Text #12

Max Range: 2.2265. Min Range: -2.2265

Max Act: 1.6136. Min Act: -0.0000

Data Index: 781619 (C4 (Web Text))

Max Activating Token Index: 839

Text #13

Max Range: 2.2265. Min Range: -2.2265

Max Act: 1.8178. Min Act: -0.0000

Data Index: 229655 (C4 (Web Text))

Max Activating Token Index: 858

Text #14

Max Range: 2.2265. Min Range: -2.2265

Max Act: 1.6622. Min Act: -0.0000

Data Index: 116267 (C4 (Web Text))

Max Activating Token Index: 680

Text #15

Max Range: 2.2265. Min Range: -2.2265

Max Act: 1.6346. Min Act: -0.0000

Data Index: 929168 (C4 (Web Text))

Max Activating Token Index: 914

Text #16

Max Range: 2.2265. Min Range: -2.2265

Max Act: 1.6024. Min Act: -0.0000

Data Index: 1545499 (Python Code)

Max Activating Token Index: 324

Text #17

Max Range: 2.2265. Min Range: -2.2265

Max Act: 1.6758. Min Act: -0.0000

Data Index: 284750 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 2.2265. Min Range: -2.2265

Max Act: 1.6927. Min Act: -0.0000

Data Index: 827611 (C4 (Web Text))

Max Activating Token Index: 998

Text #19

Max Range: 2.2265. Min Range: -2.2265

Max Act: 1.5793. Min Act: -0.0000

Data Index: 778618 (C4 (Web Text))

Max Activating Token Index: 553