Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1337 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0034. Min Act: -0.0004

Data Index: 373896 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0033. Min Act: -0.0006

Data Index: 689515 (C4 (Web Text))

Max Activating Token Index: 956

Text #2

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0032. Min Act: -0.0005

Data Index: 1015069 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0030. Min Act: -0.0006

Data Index: 1011725 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0029. Min Act: -0.0006

Data Index: 419204 (C4 (Web Text))

Max Activating Token Index: 388

Text #5

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0028. Min Act: -0.0005

Data Index: 147228 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0028. Min Act: -0.0006

Data Index: 1357091 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0028. Min Act: -0.0006

Data Index: 430476 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0027. Min Act: -0.0006

Data Index: 349853 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0028. Min Act: -0.0005

Data Index: 945377 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0027. Min Act: -0.0006

Data Index: 146837 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0027. Min Act: -0.0006

Data Index: 1218653 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0026. Min Act: -0.0006

Data Index: 1335145 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0026. Min Act: -0.0006

Data Index: 345451 (C4 (Web Text))

Max Activating Token Index: 432

Text #14

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0026. Min Act: -0.0006

Data Index: 598857 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0025. Min Act: -0.0006

Data Index: 895026 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0025. Min Act: -0.0006

Data Index: 805867 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0025. Min Act: -0.0006

Data Index: 98239 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0025. Min Act: -0.0006

Data Index: 1598445 (Python Code)

Max Activating Token Index: 370

Text #19

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0025. Min Act: -0.0005

Data Index: 795372 (C4 (Web Text))

Max Activating Token Index: 514