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

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

Neuron 4445 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.1483. Min Range: -6.1483

Max Act: 6.1483. Min Act: -0.0000

Data Index: 730805 (C4 (Web Text))

Max Activating Token Index: 1016

Text #1

Max Range: 6.1483. Min Range: -6.1483

Max Act: 5.3559. Min Act: -0.0000

Data Index: 900075 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 6.1483. Min Range: -6.1483

Max Act: 3.3734. Min Act: -0.0001

Data Index: 331793 (C4 (Web Text))

Max Activating Token Index: 480

Text #3

Max Range: 6.1483. Min Range: -6.1483

Max Act: 3.0961. Min Act: -0.0001

Data Index: 752879 (C4 (Web Text))

Max Activating Token Index: 560

Text #4

Max Range: 6.1483. Min Range: -6.1483

Max Act: 3.1634. Min Act: -0.0000

Data Index: 51169 (C4 (Web Text))

Max Activating Token Index: 514

Text #5

Max Range: 6.1483. Min Range: -6.1483

Max Act: 3.1600. Min Act: -0.0000

Data Index: 793120 (C4 (Web Text))

Max Activating Token Index: 175

Text #6

Max Range: 6.1483. Min Range: -6.1483

Max Act: 3.0102. Min Act: -0.0001

Data Index: 883745 (C4 (Web Text))

Max Activating Token Index: 349

Text #7

Max Range: 6.1483. Min Range: -6.1483

Max Act: 3.1315. Min Act: -0.0001

Data Index: 1197582 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 6.1483. Min Range: -6.1483

Max Act: 2.9255. Min Act: -0.0000

Data Index: 1021225 (C4 (Web Text))

Max Activating Token Index: 504

Text #9

Max Range: 6.1483. Min Range: -6.1483

Max Act: 3.0651. Min Act: -0.0000

Data Index: 581098 (C4 (Web Text))

Max Activating Token Index: 459

Text #10

Max Range: 6.1483. Min Range: -6.1483

Max Act: 3.2006. Min Act: -0.0000

Data Index: 915039 (C4 (Web Text))

Max Activating Token Index: 575

Text #11

Max Range: 6.1483. Min Range: -6.1483

Max Act: 3.0461. Min Act: -0.0001

Data Index: 552600 (C4 (Web Text))

Max Activating Token Index: 751

Text #12

Max Range: 6.1483. Min Range: -6.1483

Max Act: 2.9194. Min Act: -0.0001

Data Index: 158614 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 6.1483. Min Range: -6.1483

Max Act: 3.1862. Min Act: -0.0000

Data Index: 325597 (C4 (Web Text))

Max Activating Token Index: 821

Text #14

Max Range: 6.1483. Min Range: -6.1483

Max Act: 3.0335. Min Act: -0.0001

Data Index: 595004 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 6.1483. Min Range: -6.1483

Max Act: 3.0432. Min Act: -0.0001

Data Index: 289353 (C4 (Web Text))

Max Activating Token Index: 572

Text #16

Max Range: 6.1483. Min Range: -6.1483

Max Act: 3.0378. Min Act: -0.0001

Data Index: 679660 (C4 (Web Text))

Max Activating Token Index: 610

Text #17

Max Range: 6.1483. Min Range: -6.1483

Max Act: 3.1363. Min Act: -0.0001

Data Index: 1151935 (C4 (Web Text))

Max Activating Token Index: 324

Text #18

Max Range: 6.1483. Min Range: -6.1483

Max Act: 3.0067. Min Act: -0.0001

Data Index: 311603 (C4 (Web Text))

Max Activating Token Index: 825

Text #19

Max Range: 6.1483. Min Range: -6.1483

Max Act: 2.9972. Min Act: -0.0001

Data Index: 17560 (C4 (Web Text))

Max Activating Token Index: 60