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

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

Neuron 3309 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6078. Min Range: -1.6078

Max Act: 1.6078. Min Act: -0.0001

Data Index: 1467014 (Python Code)

Max Activating Token Index: 10

Text #1

Max Range: 1.6078. Min Range: -1.6078

Max Act: 1.5255. Min Act: -0.0001

Data Index: 745456 (C4 (Web Text))

Max Activating Token Index: 794

Text #2

Max Range: 1.6078. Min Range: -1.6078

Max Act: 1.4610. Min Act: -0.0001

Data Index: 1515345 (Python Code)

Max Activating Token Index: 982

Text #3

Max Range: 1.6078. Min Range: -1.6078

Max Act: 1.4677. Min Act: -0.0001

Data Index: 547399 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 1.6078. Min Range: -1.6078

Max Act: 1.3017. Min Act: -0.0001

Data Index: 380694 (C4 (Web Text))

Max Activating Token Index: 681

Text #5

Max Range: 1.6078. Min Range: -1.6078

Max Act: 1.3102. Min Act: -0.0001

Data Index: 959510 (C4 (Web Text))

Max Activating Token Index: 1015

Text #6

Max Range: 1.6078. Min Range: -1.6078

Max Act: 1.3025. Min Act: -0.0001

Data Index: 925699 (C4 (Web Text))

Max Activating Token Index: 225

Text #7

Max Range: 1.6078. Min Range: -1.6078

Max Act: 1.2959. Min Act: -0.0001

Data Index: 1216538 (C4 (Web Text))

Max Activating Token Index: 438

Text #8

Max Range: 1.6078. Min Range: -1.6078

Max Act: 1.1834. Min Act: -0.0001

Data Index: 1058693 (C4 (Web Text))

Max Activating Token Index: 699

Text #9

Max Range: 1.6078. Min Range: -1.6078

Max Act: 1.2856. Min Act: -0.0001

Data Index: 456710 (C4 (Web Text))

Max Activating Token Index: 578

Text #10

Max Range: 1.6078. Min Range: -1.6078

Max Act: 1.1707. Min Act: -0.0001

Data Index: 468412 (C4 (Web Text))

Max Activating Token Index: 498

Text #11

Max Range: 1.6078. Min Range: -1.6078

Max Act: 1.2762. Min Act: -0.0001

Data Index: 390788 (C4 (Web Text))

Max Activating Token Index: 809

Text #12

Max Range: 1.6078. Min Range: -1.6078

Max Act: 1.1847. Min Act: -0.0001

Data Index: 811624 (C4 (Web Text))

Max Activating Token Index: 879

Text #13

Max Range: 1.6078. Min Range: -1.6078

Max Act: 1.1968. Min Act: -0.0001

Data Index: 283605 (C4 (Web Text))

Max Activating Token Index: 2

Text #14

Max Range: 1.6078. Min Range: -1.6078

Max Act: 1.0868. Min Act: -0.0001

Data Index: 814417 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 1.6078. Min Range: -1.6078

Max Act: 1.1559. Min Act: -0.0001

Data Index: 1532625 (Python Code)

Max Activating Token Index: 263

Text #16

Max Range: 1.6078. Min Range: -1.6078

Max Act: 1.2082. Min Act: -0.0001

Data Index: 29659 (C4 (Web Text))

Max Activating Token Index: 261

Text #17

Max Range: 1.6078. Min Range: -1.6078

Max Act: 1.2053. Min Act: -0.0001

Data Index: 676111 (C4 (Web Text))

Max Activating Token Index: 109

Text #18

Max Range: 1.6078. Min Range: -1.6078

Max Act: 1.1044. Min Act: -0.0001

Data Index: 591893 (C4 (Web Text))

Max Activating Token Index: 84

Text #19

Max Range: 1.6078. Min Range: -1.6078

Max Act: 1.2408. Min Act: -0.0001

Data Index: 1256673 (C4 (Web Text))

Max Activating Token Index: 736