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

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

Neuron 539 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3807. Min Range: -1.3807

Max Act: 1.3807. Min Act: -0.0002

Data Index: 1186591 (C4 (Web Text))

Max Activating Token Index: 343

Text #1

Max Range: 1.3807. Min Range: -1.3807

Max Act: 1.3347. Min Act: -0.0002

Data Index: 842246 (C4 (Web Text))

Max Activating Token Index: 366

Text #2

Max Range: 1.3807. Min Range: -1.3807

Max Act: 1.2198. Min Act: -0.0002

Data Index: 455477 (C4 (Web Text))

Max Activating Token Index: 574

Text #3

Max Range: 1.3807. Min Range: -1.3807

Max Act: 1.1805. Min Act: -0.0001

Data Index: 1295524 (C4 (Web Text))

Max Activating Token Index: 239

Text #4

Max Range: 1.3807. Min Range: -1.3807

Max Act: 1.2313. Min Act: -0.0002

Data Index: 346320 (C4 (Web Text))

Max Activating Token Index: 117

Text #5

Max Range: 1.3807. Min Range: -1.3807

Max Act: 1.2872. Min Act: -0.0002

Data Index: 1158720 (C4 (Web Text))

Max Activating Token Index: 994

Text #6

Max Range: 1.3807. Min Range: -1.3807

Max Act: 1.2486. Min Act: -0.0002

Data Index: 926739 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 1.3807. Min Range: -1.3807

Max Act: 1.1442. Min Act: -0.0002

Data Index: 32328 (C4 (Web Text))

Max Activating Token Index: 115

Text #8

Max Range: 1.3807. Min Range: -1.3807

Max Act: 1.0973. Min Act: -0.0002

Data Index: 1194121 (C4 (Web Text))

Max Activating Token Index: 63

Text #9

Max Range: 1.3807. Min Range: -1.3807

Max Act: 1.1490. Min Act: -0.0001

Data Index: 472082 (C4 (Web Text))

Max Activating Token Index: 473

Text #10

Max Range: 1.3807. Min Range: -1.3807

Max Act: 1.0782. Min Act: -0.0002

Data Index: 1034339 (C4 (Web Text))

Max Activating Token Index: 47

Text #11

Max Range: 1.3807. Min Range: -1.3807

Max Act: 0.9872. Min Act: -0.0002

Data Index: 16229 (C4 (Web Text))

Max Activating Token Index: 112

Text #12

Max Range: 1.3807. Min Range: -1.3807

Max Act: 1.1003. Min Act: -0.0002

Data Index: 926877 (C4 (Web Text))

Max Activating Token Index: 553

Text #13

Max Range: 1.3807. Min Range: -1.3807

Max Act: 1.0879. Min Act: -0.0001

Data Index: 920405 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 1.3807. Min Range: -1.3807

Max Act: 1.1202. Min Act: -0.0001

Data Index: 391643 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 1.3807. Min Range: -1.3807

Max Act: 1.0454. Min Act: -0.0001

Data Index: 933913 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 1.3807. Min Range: -1.3807

Max Act: 1.0647. Min Act: -0.0002

Data Index: 1126899 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 1.3807. Min Range: -1.3807

Max Act: 0.9975. Min Act: -0.0002

Data Index: 728629 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 1.3807. Min Range: -1.3807

Max Act: 1.1165. Min Act: -0.0001

Data Index: 1066891 (C4 (Web Text))

Max Activating Token Index: 895

Text #19

Max Range: 1.3807. Min Range: -1.3807

Max Act: 0.9512. Min Act: -0.0002

Data Index: 410464 (C4 (Web Text))

Max Activating Token Index: 671