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

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

Neuron 2998 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.7797. Min Act: -0.0000

Data Index: 1101123 (C4 (Web Text))

Max Activating Token Index: 176

Text #1

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.5536. Min Act: -0.0000

Data Index: 401147 (C4 (Web Text))

Max Activating Token Index: 1015

Text #2

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.5724. Min Act: -0.0000

Data Index: 449870 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.6293. Min Act: -0.0000

Data Index: 753308 (C4 (Web Text))

Max Activating Token Index: 627

Text #4

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.5263. Min Act: -0.0000

Data Index: 102261 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.5260. Min Act: -0.0000

Data Index: 584763 (C4 (Web Text))

Max Activating Token Index: 342

Text #6

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.5218. Min Act: -0.0000

Data Index: 740723 (C4 (Web Text))

Max Activating Token Index: 442

Text #7

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.5200. Min Act: -0.0000

Data Index: 805848 (C4 (Web Text))

Max Activating Token Index: 672

Text #8

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.5184. Min Act: -0.0000

Data Index: 468615 (C4 (Web Text))

Max Activating Token Index: 561

Text #9

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.5106. Min Act: -0.0000

Data Index: 1345733 (C4 (Web Text))

Max Activating Token Index: 312

Text #10

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.4871. Min Act: -0.0000

Data Index: 643904 (C4 (Web Text))

Max Activating Token Index: 874

Text #11

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.5010. Min Act: -0.0000

Data Index: 1270187 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.5550. Min Act: -0.0000

Data Index: 1244743 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.5000. Min Act: -0.0000

Data Index: 390826 (C4 (Web Text))

Max Activating Token Index: 363

Text #14

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.4921. Min Act: -0.0000

Data Index: 1210304 (C4 (Web Text))

Max Activating Token Index: 915

Text #15

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.4886. Min Act: -0.0000

Data Index: 759625 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.4912. Min Act: -0.0000

Data Index: 263557 (C4 (Web Text))

Max Activating Token Index: 307

Text #17

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.4746. Min Act: -0.0000

Data Index: 1288013 (C4 (Web Text))

Max Activating Token Index: 1016

Text #18

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.4673. Min Act: -0.0000

Data Index: 54325 (C4 (Web Text))

Max Activating Token Index: 619

Text #19

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.4866. Min Act: -0.0000

Data Index: 969583 (C4 (Web Text))

Max Activating Token Index: 237