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

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

Neuron 3134 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: 1.6907. Min Range: -1.6907

Max Act: 1.6423. Min Act: -0.0001

Data Index: 268028 (C4 (Web Text))

Max Activating Token Index: 441

Text #1

Max Range: 1.6907. Min Range: -1.6907

Max Act: 1.6907. Min Act: -0.0001

Data Index: 297152 (C4 (Web Text))

Max Activating Token Index: 844

Text #2

Max Range: 1.6907. Min Range: -1.6907

Max Act: 1.5206. Min Act: -0.0001

Data Index: 613920 (C4 (Web Text))

Max Activating Token Index: 762

Text #3

Max Range: 1.6907. Min Range: -1.6907

Max Act: 1.5239. Min Act: -0.0001

Data Index: 1266069 (C4 (Web Text))

Max Activating Token Index: 846

Text #4

Max Range: 1.6907. Min Range: -1.6907

Max Act: 1.5086. Min Act: -0.0001

Data Index: 294267 (C4 (Web Text))

Max Activating Token Index: 597

Text #5

Max Range: 1.6907. Min Range: -1.6907

Max Act: 1.4055. Min Act: -0.0001

Data Index: 1029567 (C4 (Web Text))

Max Activating Token Index: 914

Text #6

Max Range: 1.6907. Min Range: -1.6907

Max Act: 1.3944. Min Act: -0.0001

Data Index: 594531 (C4 (Web Text))

Max Activating Token Index: 852

Text #7

Max Range: 1.6907. Min Range: -1.6907

Max Act: 1.2704. Min Act: -0.0001

Data Index: 751646 (C4 (Web Text))

Max Activating Token Index: 859

Text #8

Max Range: 1.6907. Min Range: -1.6907

Max Act: 1.2931. Min Act: -0.0001

Data Index: 324886 (C4 (Web Text))

Max Activating Token Index: 627

Text #9

Max Range: 1.6907. Min Range: -1.6907

Max Act: 1.3020. Min Act: -0.0001

Data Index: 1201965 (C4 (Web Text))

Max Activating Token Index: 404

Text #10

Max Range: 1.6907. Min Range: -1.6907

Max Act: 1.3112. Min Act: -0.0001

Data Index: 1204902 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 1.6907. Min Range: -1.6907

Max Act: 1.3588. Min Act: -0.0001

Data Index: 259844 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 1.6907. Min Range: -1.6907

Max Act: 1.2286. Min Act: -0.0001

Data Index: 365754 (C4 (Web Text))

Max Activating Token Index: 665

Text #13

Max Range: 1.6907. Min Range: -1.6907

Max Act: 1.2892. Min Act: -0.0001

Data Index: 750092 (C4 (Web Text))

Max Activating Token Index: 245

Text #14

Max Range: 1.6907. Min Range: -1.6907

Max Act: 1.2179. Min Act: -0.0001

Data Index: 69415 (C4 (Web Text))

Max Activating Token Index: 425

Text #15

Max Range: 1.6907. Min Range: -1.6907

Max Act: 1.1915. Min Act: -0.0001

Data Index: 419647 (C4 (Web Text))

Max Activating Token Index: 43

Text #16

Max Range: 1.6907. Min Range: -1.6907

Max Act: 1.1936. Min Act: -0.0001

Data Index: 747609 (C4 (Web Text))

Max Activating Token Index: 780

Text #17

Max Range: 1.6907. Min Range: -1.6907

Max Act: 1.1851. Min Act: -0.0001

Data Index: 350184 (C4 (Web Text))

Max Activating Token Index: 465

Text #18

Max Range: 1.6907. Min Range: -1.6907

Max Act: 1.1948. Min Act: -0.0001

Data Index: 1183391 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 1.6907. Min Range: -1.6907

Max Act: 1.2525. Min Act: -0.0001

Data Index: 830460 (C4 (Web Text))

Max Activating Token Index: 609