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

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

Neuron 3845 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.5816. Min Act: -0.0000

Data Index: 145234 (C4 (Web Text))

Max Activating Token Index: 239

Text #1

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.5937. Min Act: 0.0001

Data Index: 1214729 (C4 (Web Text))

Max Activating Token Index: 246

Text #2

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.5824. Min Act: -0.0000

Data Index: 784040 (C4 (Web Text))

Max Activating Token Index: 183

Text #3

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.5443. Min Act: 0.0001

Data Index: 365636 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.5725. Min Act: 0.0000

Data Index: 768770 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.5138. Min Act: 0.0000

Data Index: 49206 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.5500. Min Act: -0.0000

Data Index: 219910 (C4 (Web Text))

Max Activating Token Index: 585

Text #7

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.5051. Min Act: 0.0000

Data Index: 252230 (C4 (Web Text))

Max Activating Token Index: 928

Text #8

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.4994. Min Act: -0.0000

Data Index: 1278448 (C4 (Web Text))

Max Activating Token Index: 629

Text #9

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.5275. Min Act: 0.0000

Data Index: 1171951 (C4 (Web Text))

Max Activating Token Index: 244

Text #10

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.4893. Min Act: 0.0001

Data Index: 1198870 (C4 (Web Text))

Max Activating Token Index: 633

Text #11

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.5244. Min Act: 0.0001

Data Index: 1046340 (C4 (Web Text))

Max Activating Token Index: 54

Text #12

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.4968. Min Act: -0.0000

Data Index: 937825 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.4794. Min Act: 0.0000

Data Index: 8877 (C4 (Web Text))

Max Activating Token Index: 307

Text #14

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.4776. Min Act: -0.0000

Data Index: 951532 (C4 (Web Text))

Max Activating Token Index: 888

Text #15

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.4914. Min Act: 0.0000

Data Index: 758356 (C4 (Web Text))

Max Activating Token Index: 471

Text #16

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.4784. Min Act: 0.0000

Data Index: 919725 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.5117. Min Act: 0.0001

Data Index: 1304238 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.4812. Min Act: 0.0000

Data Index: 165744 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.5002. Min Act: 0.0001

Data Index: 783932 (C4 (Web Text))

Max Activating Token Index: 890