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

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

Neuron 3711 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.2120. Min Act: -0.0000

Data Index: 1170408 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.2031. Min Act: -0.0000

Data Index: 915130 (C4 (Web Text))

Max Activating Token Index: 28

Text #2

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.2064. Min Act: -0.0000

Data Index: 916956 (C4 (Web Text))

Max Activating Token Index: 927

Text #3

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.1880. Min Act: -0.0000

Data Index: 38079 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.1949. Min Act: -0.0000

Data Index: 333589 (C4 (Web Text))

Max Activating Token Index: 529

Text #5

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.2001. Min Act: -0.0000

Data Index: 516359 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.2023. Min Act: -0.0000

Data Index: 73625 (C4 (Web Text))

Max Activating Token Index: 348

Text #7

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.1906. Min Act: -0.0000

Data Index: 931786 (C4 (Web Text))

Max Activating Token Index: 396

Text #8

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.1735. Min Act: -0.0000

Data Index: 796050 (C4 (Web Text))

Max Activating Token Index: 685

Text #9

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.1875. Min Act: -0.0000

Data Index: 45001 (C4 (Web Text))

Max Activating Token Index: 292

Text #10

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.1862. Min Act: -0.0000

Data Index: 427262 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.1853. Min Act: -0.0000

Data Index: 995316 (C4 (Web Text))

Max Activating Token Index: 1013

Text #12

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.1706. Min Act: -0.0000

Data Index: 1083322 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.1527. Min Act: -0.0000

Data Index: 1111786 (C4 (Web Text))

Max Activating Token Index: 642

Text #14

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.1647. Min Act: -0.0000

Data Index: 876246 (C4 (Web Text))

Max Activating Token Index: 610

Text #15

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.1720. Min Act: -0.0000

Data Index: 797783 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.1687. Min Act: -0.0000

Data Index: 331224 (C4 (Web Text))

Max Activating Token Index: 877

Text #17

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.1750. Min Act: -0.0000

Data Index: 266588 (C4 (Web Text))

Max Activating Token Index: 1018

Text #18

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.1614. Min Act: -0.0000

Data Index: 1146573 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.1578. Min Act: -0.0000

Data Index: 1142188 (C4 (Web Text))

Max Activating Token Index: 75