Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3059 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5753. Min Range: -1.5753

Max Act: 1.5174. Min Act: -0.0000

Data Index: 860556 (C4 (Web Text))

Max Activating Token Index: 905

Text #1

Max Range: 1.5753. Min Range: -1.5753

Max Act: 1.5753. Min Act: -0.0000

Data Index: 140007 (C4 (Web Text))

Max Activating Token Index: 486

Text #2

Max Range: 1.5753. Min Range: -1.5753

Max Act: 1.4755. Min Act: -0.0000

Data Index: 1349178 (C4 (Web Text))

Max Activating Token Index: 888

Text #3

Max Range: 1.5753. Min Range: -1.5753

Max Act: 1.4060. Min Act: -0.0000

Data Index: 5685 (C4 (Web Text))

Max Activating Token Index: 1022

Text #4

Max Range: 1.5753. Min Range: -1.5753

Max Act: 1.2182. Min Act: -0.0000

Data Index: 1111257 (C4 (Web Text))

Max Activating Token Index: 141

Text #5

Max Range: 1.5753. Min Range: -1.5753

Max Act: 1.1492. Min Act: -0.0000

Data Index: 1287360 (C4 (Web Text))

Max Activating Token Index: 717

Text #6

Max Range: 1.5753. Min Range: -1.5753

Max Act: 1.3585. Min Act: -0.0000

Data Index: 1014236 (C4 (Web Text))

Max Activating Token Index: 666

Text #7

Max Range: 1.5753. Min Range: -1.5753

Max Act: 1.2865. Min Act: -0.0000

Data Index: 944510 (C4 (Web Text))

Max Activating Token Index: 441

Text #8

Max Range: 1.5753. Min Range: -1.5753

Max Act: 1.1870. Min Act: -0.0000

Data Index: 1341230 (C4 (Web Text))

Max Activating Token Index: 688

Text #9

Max Range: 1.5753. Min Range: -1.5753

Max Act: 1.4002. Min Act: -0.0000

Data Index: 87311 (C4 (Web Text))

Max Activating Token Index: 260

Text #10

Max Range: 1.5753. Min Range: -1.5753

Max Act: 1.1611. Min Act: -0.0000

Data Index: 1275420 (C4 (Web Text))

Max Activating Token Index: 746

Text #11

Max Range: 1.5753. Min Range: -1.5753

Max Act: 1.0357. Min Act: -0.0000

Data Index: 817517 (C4 (Web Text))

Max Activating Token Index: 352

Text #12

Max Range: 1.5753. Min Range: -1.5753

Max Act: 0.9952. Min Act: -0.0000

Data Index: 133969 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 1.5753. Min Range: -1.5753

Max Act: 1.0431. Min Act: -0.0000

Data Index: 1195354 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 1.5753. Min Range: -1.5753

Max Act: 1.0114. Min Act: -0.0000

Data Index: 259267 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 1.5753. Min Range: -1.5753

Max Act: 0.9742. Min Act: -0.0000

Data Index: 1044432 (C4 (Web Text))

Max Activating Token Index: 508

Text #16

Max Range: 1.5753. Min Range: -1.5753

Max Act: 0.9067. Min Act: -0.0000

Data Index: 474689 (C4 (Web Text))

Max Activating Token Index: 729

Text #17

Max Range: 1.5753. Min Range: -1.5753

Max Act: 0.9773. Min Act: -0.0000

Data Index: 1177593 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 1.5753. Min Range: -1.5753

Max Act: 0.9132. Min Act: -0.0000

Data Index: 1018572 (C4 (Web Text))

Max Activating Token Index: 862

Text #19

Max Range: 1.5753. Min Range: -1.5753

Max Act: 0.9313. Min Act: -0.0000

Data Index: 748698 (C4 (Web Text))

Max Activating Token Index: 831