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

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

Neuron 95 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: 2.1109. Min Range: -2.1109

Max Act: 2.0237. Min Act: -0.0000

Data Index: 459107 (C4 (Web Text))

Max Activating Token Index: 999

Text #1

Max Range: 2.1109. Min Range: -2.1109

Max Act: 2.1109. Min Act: -0.0000

Data Index: 823690 (C4 (Web Text))

Max Activating Token Index: 629

Text #2

Max Range: 2.1109. Min Range: -2.1109

Max Act: 2.0925. Min Act: -0.0000

Data Index: 1056857 (C4 (Web Text))

Max Activating Token Index: 534

Text #3

Max Range: 2.1109. Min Range: -2.1109

Max Act: 2.0314. Min Act: -0.0000

Data Index: 746547 (C4 (Web Text))

Max Activating Token Index: 793

Text #4

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.9699. Min Act: -0.0000

Data Index: 731639 (C4 (Web Text))

Max Activating Token Index: 251

Text #5

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.7783. Min Act: -0.0000

Data Index: 727687 (C4 (Web Text))

Max Activating Token Index: 328

Text #6

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.8415. Min Act: -0.0000

Data Index: 1312032 (C4 (Web Text))

Max Activating Token Index: 163

Text #7

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.9340. Min Act: -0.0000

Data Index: 259015 (C4 (Web Text))

Max Activating Token Index: 435

Text #8

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.7181. Min Act: -0.0000

Data Index: 1233833 (C4 (Web Text))

Max Activating Token Index: 437

Text #9

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.7887. Min Act: -0.0000

Data Index: 252069 (C4 (Web Text))

Max Activating Token Index: 833

Text #10

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.6989. Min Act: -0.0000

Data Index: 167671 (C4 (Web Text))

Max Activating Token Index: 970

Text #11

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.6610. Min Act: -0.0000

Data Index: 284869 (C4 (Web Text))

Max Activating Token Index: 868

Text #12

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.8536. Min Act: -0.0000

Data Index: 1351115 (C4 (Web Text))

Max Activating Token Index: 500

Text #13

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.6367. Min Act: -0.0000

Data Index: 8806 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.7364. Min Act: -0.0000

Data Index: 1093169 (C4 (Web Text))

Max Activating Token Index: 388

Text #15

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.8126. Min Act: -0.0000

Data Index: 196590 (C4 (Web Text))

Max Activating Token Index: 591

Text #16

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.7244. Min Act: -0.0000

Data Index: 287615 (C4 (Web Text))

Max Activating Token Index: 77

Text #17

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.7941. Min Act: -0.0001

Data Index: 325663 (C4 (Web Text))

Max Activating Token Index: 989

Text #18

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.5944. Min Act: -0.0000

Data Index: 825229 (C4 (Web Text))

Max Activating Token Index: 563

Text #19

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.6672. Min Act: -0.0000

Data Index: 125104 (C4 (Web Text))

Max Activating Token Index: 302