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

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

Neuron 520 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.9696. Min Act: -0.0000

Data Index: 1096643 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.6812. Min Act: -0.0000

Data Index: 471141 (C4 (Web Text))

Max Activating Token Index: 953

Text #2

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.6244. Min Act: -0.0000

Data Index: 19910 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.6567. Min Act: -0.0000

Data Index: 1095020 (C4 (Web Text))

Max Activating Token Index: 811

Text #4

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.4370. Min Act: -0.0000

Data Index: 1093315 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.4627. Min Act: -0.0000

Data Index: 893266 (C4 (Web Text))

Max Activating Token Index: 543

Text #6

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.3939. Min Act: -0.0000

Data Index: 416403 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.3125. Min Act: -0.0000

Data Index: 177032 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.3580. Min Act: -0.0000

Data Index: 945003 (C4 (Web Text))

Max Activating Token Index: 275

Text #9

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.3467. Min Act: -0.0000

Data Index: 134287 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.3493. Min Act: -0.0000

Data Index: 1140207 (C4 (Web Text))

Max Activating Token Index: 49

Text #11

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.3124. Min Act: -0.0000

Data Index: 496581 (C4 (Web Text))

Max Activating Token Index: 866

Text #12

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.2930. Min Act: -0.0000

Data Index: 652851 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.2782. Min Act: -0.0000

Data Index: 947138 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.3044. Min Act: -0.0000

Data Index: 444862 (C4 (Web Text))

Max Activating Token Index: 216

Text #15

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.3414. Min Act: -0.0000

Data Index: 1358302 (C4 (Web Text))

Max Activating Token Index: 232

Text #16

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.2947. Min Act: -0.0000

Data Index: 806009 (C4 (Web Text))

Max Activating Token Index: 18

Text #17

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.2187. Min Act: -0.0000

Data Index: 618004 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.2059. Min Act: -0.0000

Data Index: 357458 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.2531. Min Act: -0.0000

Data Index: 487181 (C4 (Web Text))

Max Activating Token Index: 31