Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1330 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1109. Min Act: 0.0002

Data Index: 616087 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0980. Min Act: 0.0000

Data Index: 767746 (C4 (Web Text))

Max Activating Token Index: 420

Text #2

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0959. Min Act: -0.0001

Data Index: 467657 (C4 (Web Text))

Max Activating Token Index: 118

Text #3

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0731. Min Act: 0.0001

Data Index: 323164 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0970. Min Act: -0.0001

Data Index: 236087 (C4 (Web Text))

Max Activating Token Index: 245

Text #5

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0690. Min Act: 0.0000

Data Index: 252920 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0686. Min Act: -0.0000

Data Index: 1097000 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0962. Min Act: -0.0001

Data Index: 1059614 (C4 (Web Text))

Max Activating Token Index: 759

Text #8

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0644. Min Act: -0.0000

Data Index: 1110406 (C4 (Web Text))

Max Activating Token Index: 490

Text #9

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0659. Min Act: -0.0001

Data Index: 610658 (C4 (Web Text))

Max Activating Token Index: 359

Text #10

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0358. Min Act: -0.0001

Data Index: 496255 (C4 (Web Text))

Max Activating Token Index: 287

Text #11

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0607. Min Act: -0.0001

Data Index: 1336375 (C4 (Web Text))

Max Activating Token Index: 338

Text #12

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0665. Min Act: -0.0001

Data Index: 739769 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0517. Min Act: -0.0001

Data Index: 1341548 (C4 (Web Text))

Max Activating Token Index: 319

Text #14

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0548. Min Act: -0.0001

Data Index: 496236 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0504. Min Act: -0.0001

Data Index: 505564 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0507. Min Act: -0.0000

Data Index: 1163377 (C4 (Web Text))

Max Activating Token Index: 194

Text #17

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0511. Min Act: 0.0000

Data Index: 384141 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0665. Min Act: -0.0001

Data Index: 1197205 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0417. Min Act: 0.0001

Data Index: 423413 (C4 (Web Text))

Max Activating Token Index: 176