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

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

Neuron 1533 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1518. Min Act: -0.0001

Data Index: 215653 (C4 (Web Text))

Max Activating Token Index: 351

Text #1

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1444. Min Act: -0.0001

Data Index: 506106 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1350. Min Act: -0.0001

Data Index: 480579 (C4 (Web Text))

Max Activating Token Index: 694

Text #3

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1396. Min Act: -0.0001

Data Index: 793209 (C4 (Web Text))

Max Activating Token Index: 404

Text #4

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1178. Min Act: -0.0001

Data Index: 134194 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1151. Min Act: -0.0001

Data Index: 852270 (C4 (Web Text))

Max Activating Token Index: 876

Text #6

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.0975. Min Act: -0.0001

Data Index: 671386 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1070. Min Act: -0.0001

Data Index: 119395 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1111. Min Act: -0.0001

Data Index: 39547 (C4 (Web Text))

Max Activating Token Index: 1004

Text #9

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.0941. Min Act: -0.0001

Data Index: 361761 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1026. Min Act: -0.0001

Data Index: 626607 (C4 (Web Text))

Max Activating Token Index: 484

Text #11

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1029. Min Act: -0.0001

Data Index: 790246 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1089. Min Act: -0.0001

Data Index: 720259 (C4 (Web Text))

Max Activating Token Index: 423

Text #13

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1116. Min Act: -0.0001

Data Index: 809520 (C4 (Web Text))

Max Activating Token Index: 245

Text #14

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.0999. Min Act: -0.0001

Data Index: 1357700 (C4 (Web Text))

Max Activating Token Index: 453

Text #15

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.0830. Min Act: -0.0001

Data Index: 1210501 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.0918. Min Act: -0.0001

Data Index: 610333 (C4 (Web Text))

Max Activating Token Index: 944

Text #17

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.0857. Min Act: -0.0001

Data Index: 182477 (C4 (Web Text))

Max Activating Token Index: 613

Text #18

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.0975. Min Act: -0.0001

Data Index: 827855 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1024. Min Act: -0.0001

Data Index: 318368 (C4 (Web Text))

Max Activating Token Index: 475