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

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

Neuron 3343 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6768. Min Range: -1.6768

Max Act: 1.6768. Min Act: -0.0000

Data Index: 865155 (C4 (Web Text))

Max Activating Token Index: 893

Text #1

Max Range: 1.6768. Min Range: -1.6768

Max Act: 1.1770. Min Act: -0.0000

Data Index: 1281013 (C4 (Web Text))

Max Activating Token Index: 295

Text #2

Max Range: 1.6768. Min Range: -1.6768

Max Act: 0.9910. Min Act: -0.0000

Data Index: 1133601 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 1.6768. Min Range: -1.6768

Max Act: 1.0149. Min Act: 0.0000

Data Index: 1064986 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 1.6768. Min Range: -1.6768

Max Act: 1.0472. Min Act: -0.0000

Data Index: 878824 (C4 (Web Text))

Max Activating Token Index: 436

Text #5

Max Range: 1.6768. Min Range: -1.6768

Max Act: 0.9975. Min Act: -0.0000

Data Index: 373247 (C4 (Web Text))

Max Activating Token Index: 958

Text #6

Max Range: 1.6768. Min Range: -1.6768

Max Act: 0.9914. Min Act: 0.0000

Data Index: 811201 (C4 (Web Text))

Max Activating Token Index: 943

Text #7

Max Range: 1.6768. Min Range: -1.6768

Max Act: 0.9428. Min Act: -0.0000

Data Index: 995435 (C4 (Web Text))

Max Activating Token Index: 65

Text #8

Max Range: 1.6768. Min Range: -1.6768

Max Act: 0.9645. Min Act: 0.0001

Data Index: 441758 (C4 (Web Text))

Max Activating Token Index: 646

Text #9

Max Range: 1.6768. Min Range: -1.6768

Max Act: 0.9430. Min Act: -0.0000

Data Index: 386784 (C4 (Web Text))

Max Activating Token Index: 964

Text #10

Max Range: 1.6768. Min Range: -1.6768

Max Act: 0.8856. Min Act: 0.0000

Data Index: 450232 (C4 (Web Text))

Max Activating Token Index: 831

Text #11

Max Range: 1.6768. Min Range: -1.6768

Max Act: 0.9022. Min Act: 0.0002

Data Index: 1069394 (C4 (Web Text))

Max Activating Token Index: 209

Text #12

Max Range: 1.6768. Min Range: -1.6768

Max Act: 0.9144. Min Act: -0.0000

Data Index: 1034331 (C4 (Web Text))

Max Activating Token Index: 216

Text #13

Max Range: 1.6768. Min Range: -1.6768

Max Act: 0.9781. Min Act: 0.0000

Data Index: 88772 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 1.6768. Min Range: -1.6768

Max Act: 0.8949. Min Act: -0.0000

Data Index: 186137 (C4 (Web Text))

Max Activating Token Index: 474

Text #15

Max Range: 1.6768. Min Range: -1.6768

Max Act: 0.8691. Min Act: -0.0000

Data Index: 535506 (C4 (Web Text))

Max Activating Token Index: 721

Text #16

Max Range: 1.6768. Min Range: -1.6768

Max Act: 0.8913. Min Act: -0.0000

Data Index: 881611 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 1.6768. Min Range: -1.6768

Max Act: 0.8785. Min Act: -0.0000

Data Index: 266783 (C4 (Web Text))

Max Activating Token Index: 205

Text #18

Max Range: 1.6768. Min Range: -1.6768

Max Act: 0.9095. Min Act: -0.0000

Data Index: 722243 (C4 (Web Text))

Max Activating Token Index: 832

Text #19

Max Range: 1.6768. Min Range: -1.6768

Max Act: 0.8814. Min Act: 0.0000

Data Index: 17023 (C4 (Web Text))

Max Activating Token Index: 146