Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 37 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3255. Min Range: -0.3255

Max Act: 0.2911. Min Act: -0.0001

Data Index: 61495 (C4 (Web Text))

Max Activating Token Index: 700

Text #1

Max Range: 0.3255. Min Range: -0.3255

Max Act: 0.3158. Min Act: -0.0001

Data Index: 1076240 (C4 (Web Text))

Max Activating Token Index: 988

Text #2

Max Range: 0.3255. Min Range: -0.3255

Max Act: 0.3056. Min Act: -0.0001

Data Index: 42893 (C4 (Web Text))

Max Activating Token Index: 867

Text #3

Max Range: 0.3255. Min Range: -0.3255

Max Act: 0.2987. Min Act: -0.0001

Data Index: 131597 (C4 (Web Text))

Max Activating Token Index: 782

Text #4

Max Range: 0.3255. Min Range: -0.3255

Max Act: 0.3081. Min Act: -0.0001

Data Index: 1054943 (C4 (Web Text))

Max Activating Token Index: 1002

Text #5

Max Range: 0.3255. Min Range: -0.3255

Max Act: 0.3199. Min Act: -0.0001

Data Index: 154105 (C4 (Web Text))

Max Activating Token Index: 886

Text #6

Max Range: 0.3255. Min Range: -0.3255

Max Act: 0.3124. Min Act: -0.0001

Data Index: 919487 (C4 (Web Text))

Max Activating Token Index: 667

Text #7

Max Range: 0.3255. Min Range: -0.3255

Max Act: 0.3117. Min Act: -0.0001

Data Index: 214826 (C4 (Web Text))

Max Activating Token Index: 765

Text #8

Max Range: 0.3255. Min Range: -0.3255

Max Act: 0.2985. Min Act: -0.0001

Data Index: 242017 (C4 (Web Text))

Max Activating Token Index: 600

Text #9

Max Range: 0.3255. Min Range: -0.3255

Max Act: 0.2854. Min Act: -0.0001

Data Index: 221858 (C4 (Web Text))

Max Activating Token Index: 826

Text #10

Max Range: 0.3255. Min Range: -0.3255

Max Act: 0.2933. Min Act: -0.0001

Data Index: 315773 (C4 (Web Text))

Max Activating Token Index: 448

Text #11

Max Range: 0.3255. Min Range: -0.3255

Max Act: 0.2994. Min Act: -0.0001

Data Index: 1030219 (C4 (Web Text))

Max Activating Token Index: 798

Text #12

Max Range: 0.3255. Min Range: -0.3255

Max Act: 0.2842. Min Act: -0.0001

Data Index: 411120 (C4 (Web Text))

Max Activating Token Index: 759

Text #13

Max Range: 0.3255. Min Range: -0.3255

Max Act: 0.3255. Min Act: -0.0001

Data Index: 536989 (C4 (Web Text))

Max Activating Token Index: 735

Text #14

Max Range: 0.3255. Min Range: -0.3255

Max Act: 0.2709. Min Act: -0.0001

Data Index: 987292 (C4 (Web Text))

Max Activating Token Index: 452

Text #15

Max Range: 0.3255. Min Range: -0.3255

Max Act: 0.2559. Min Act: -0.0001

Data Index: 959262 (C4 (Web Text))

Max Activating Token Index: 499

Text #16

Max Range: 0.3255. Min Range: -0.3255

Max Act: 0.2413. Min Act: -0.0001

Data Index: 1112792 (C4 (Web Text))

Max Activating Token Index: 712

Text #17

Max Range: 0.3255. Min Range: -0.3255

Max Act: 0.2521. Min Act: -0.0001

Data Index: 1333927 (C4 (Web Text))

Max Activating Token Index: 796

Text #18

Max Range: 0.3255. Min Range: -0.3255

Max Act: 0.2912. Min Act: -0.0001

Data Index: 930865 (C4 (Web Text))

Max Activating Token Index: 911

Text #19

Max Range: 0.3255. Min Range: -0.3255

Max Act: 0.2376. Min Act: -0.0001

Data Index: 981331 (C4 (Web Text))

Max Activating Token Index: 594