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

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

Neuron 1437 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.4927. Min Act: -0.0001

Data Index: 502508 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3405. Min Act: -0.0001

Data Index: 1006329 (C4 (Web Text))

Max Activating Token Index: 656

Text #2

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3212. Min Act: -0.0001

Data Index: 1588780 (Python Code)

Max Activating Token Index: 53

Text #3

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.2095. Min Act: -0.0001

Data Index: 1398683 (Python Code)

Max Activating Token Index: 897

Text #4

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.2247. Min Act: -0.0001

Data Index: 708795 (C4 (Web Text))

Max Activating Token Index: 311

Text #5

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.2245. Min Act: -0.0001

Data Index: 1310850 (C4 (Web Text))

Max Activating Token Index: 841

Text #6

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.2104. Min Act: -0.0001

Data Index: 382135 (C4 (Web Text))

Max Activating Token Index: 724

Text #7

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.1719. Min Act: -0.0001

Data Index: 681031 (C4 (Web Text))

Max Activating Token Index: 624

Text #8

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.2076. Min Act: -0.0001

Data Index: 137296 (C4 (Web Text))

Max Activating Token Index: 469

Text #9

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.1876. Min Act: -0.0001

Data Index: 16976 (C4 (Web Text))

Max Activating Token Index: 626

Text #10

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.2016. Min Act: -0.0001

Data Index: 54171 (C4 (Web Text))

Max Activating Token Index: 375

Text #11

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.2596. Min Act: -0.0001

Data Index: 463403 (C4 (Web Text))

Max Activating Token Index: 630

Text #12

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.1977. Min Act: -0.0001

Data Index: 1224415 (C4 (Web Text))

Max Activating Token Index: 70

Text #13

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.1992. Min Act: -0.0001

Data Index: 612766 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.1890. Min Act: -0.0001

Data Index: 502435 (C4 (Web Text))

Max Activating Token Index: 958

Text #15

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.2001. Min Act: -0.0001

Data Index: 713796 (C4 (Web Text))

Max Activating Token Index: 334

Text #16

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.1782. Min Act: -0.0001

Data Index: 1082407 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.1980. Min Act: -0.0001

Data Index: 91794 (C4 (Web Text))

Max Activating Token Index: 826

Text #18

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.1937. Min Act: -0.0001

Data Index: 1321416 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.1938. Min Act: -0.0001

Data Index: 776868 (C4 (Web Text))

Max Activating Token Index: 6