Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1011 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4468. Min Range: -1.4468

Max Act: 1.4468. Min Act: -0.0001

Data Index: 867573 (C4 (Web Text))

Max Activating Token Index: 573

Text #1

Max Range: 1.4468. Min Range: -1.4468

Max Act: 1.4238. Min Act: -0.0001

Data Index: 575963 (C4 (Web Text))

Max Activating Token Index: 451

Text #2

Max Range: 1.4468. Min Range: -1.4468

Max Act: 1.4334. Min Act: -0.0001

Data Index: 503609 (C4 (Web Text))

Max Activating Token Index: 933

Text #3

Max Range: 1.4468. Min Range: -1.4468

Max Act: 1.2931. Min Act: -0.0001

Data Index: 1095880 (C4 (Web Text))

Max Activating Token Index: 727

Text #4

Max Range: 1.4468. Min Range: -1.4468

Max Act: 1.3488. Min Act: -0.0001

Data Index: 1152330 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 1.4468. Min Range: -1.4468

Max Act: 1.3195. Min Act: -0.0001

Data Index: 704664 (C4 (Web Text))

Max Activating Token Index: 694

Text #6

Max Range: 1.4468. Min Range: -1.4468

Max Act: 1.2807. Min Act: -0.0001

Data Index: 705884 (C4 (Web Text))

Max Activating Token Index: 691

Text #7

Max Range: 1.4468. Min Range: -1.4468

Max Act: 1.3031. Min Act: -0.0001

Data Index: 381237 (C4 (Web Text))

Max Activating Token Index: 812

Text #8

Max Range: 1.4468. Min Range: -1.4468

Max Act: 1.2316. Min Act: -0.0001

Data Index: 1117909 (C4 (Web Text))

Max Activating Token Index: 477

Text #9

Max Range: 1.4468. Min Range: -1.4468

Max Act: 1.2904. Min Act: -0.0001

Data Index: 1236675 (C4 (Web Text))

Max Activating Token Index: 942

Text #10

Max Range: 1.4468. Min Range: -1.4468

Max Act: 1.1644. Min Act: -0.0001

Data Index: 935907 (C4 (Web Text))

Max Activating Token Index: 273

Text #11

Max Range: 1.4468. Min Range: -1.4468

Max Act: 1.1899. Min Act: -0.0001

Data Index: 213716 (C4 (Web Text))

Max Activating Token Index: 745

Text #12

Max Range: 1.4468. Min Range: -1.4468

Max Act: 1.1274. Min Act: -0.0001

Data Index: 927718 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 1.4468. Min Range: -1.4468

Max Act: 1.1587. Min Act: -0.0001

Data Index: 844920 (C4 (Web Text))

Max Activating Token Index: 790

Text #14

Max Range: 1.4468. Min Range: -1.4468

Max Act: 1.0889. Min Act: -0.0001

Data Index: 1238398 (C4 (Web Text))

Max Activating Token Index: 355

Text #15

Max Range: 1.4468. Min Range: -1.4468

Max Act: 1.1808. Min Act: -0.0001

Data Index: 97323 (C4 (Web Text))

Max Activating Token Index: 529

Text #16

Max Range: 1.4468. Min Range: -1.4468

Max Act: 1.1418. Min Act: -0.0001

Data Index: 421807 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 1.4468. Min Range: -1.4468

Max Act: 1.0979. Min Act: -0.0001

Data Index: 1143714 (C4 (Web Text))

Max Activating Token Index: 936

Text #18

Max Range: 1.4468. Min Range: -1.4468

Max Act: 1.0521. Min Act: -0.0001

Data Index: 202139 (C4 (Web Text))

Max Activating Token Index: 841

Text #19

Max Range: 1.4468. Min Range: -1.4468

Max Act: 1.1119. Min Act: -0.0001

Data Index: 604018 (C4 (Web Text))

Max Activating Token Index: 459