Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1436 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0979. Min Act: -0.0002

Data Index: 502371 (C4 (Web Text))

Max Activating Token Index: 504

Text #1

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0972. Min Act: -0.0002

Data Index: 623892 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0987. Min Act: -0.0002

Data Index: 122953 (C4 (Web Text))

Max Activating Token Index: 693

Text #3

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0921. Min Act: -0.0002

Data Index: 90062 (C4 (Web Text))

Max Activating Token Index: 736

Text #4

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0917. Min Act: -0.0002

Data Index: 648748 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0900. Min Act: -0.0002

Data Index: 308774 (C4 (Web Text))

Max Activating Token Index: 18

Text #6

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0911. Min Act: -0.0002

Data Index: 547844 (C4 (Web Text))

Max Activating Token Index: 309

Text #7

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0873. Min Act: -0.0002

Data Index: 349687 (C4 (Web Text))

Max Activating Token Index: 543

Text #8

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0855. Min Act: -0.0002

Data Index: 514708 (C4 (Web Text))

Max Activating Token Index: 408

Text #9

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0875. Min Act: -0.0002

Data Index: 817678 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0831. Min Act: -0.0002

Data Index: 343448 (C4 (Web Text))

Max Activating Token Index: 468

Text #11

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0815. Min Act: -0.0002

Data Index: 29181 (C4 (Web Text))

Max Activating Token Index: 579

Text #12

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0827. Min Act: -0.0002

Data Index: 452332 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0840. Min Act: -0.0002

Data Index: 418297 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0822. Min Act: -0.0002

Data Index: 1040040 (C4 (Web Text))

Max Activating Token Index: 209

Text #15

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0833. Min Act: -0.0002

Data Index: 691926 (C4 (Web Text))

Max Activating Token Index: 326

Text #16

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0826. Min Act: -0.0002

Data Index: 1322148 (C4 (Web Text))

Max Activating Token Index: 354

Text #17

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0808. Min Act: -0.0002

Data Index: 1238915 (C4 (Web Text))

Max Activating Token Index: 706

Text #18

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0866. Min Act: -0.0002

Data Index: 1193652 (C4 (Web Text))

Max Activating Token Index: 858

Text #19

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0835. Min Act: -0.0002

Data Index: 1120207 (C4 (Web Text))

Max Activating Token Index: 97