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

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

Neuron 2038 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0035. Min Act: -0.0005

Data Index: 870305 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0034. Min Act: -0.0006

Data Index: 803442 (C4 (Web Text))

Max Activating Token Index: 49

Text #2

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0034. Min Act: -0.0005

Data Index: 699845 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0032. Min Act: -0.0005

Data Index: 397965 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0032. Min Act: -0.0005

Data Index: 1087566 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0031. Min Act: -0.0005

Data Index: 742512 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0031. Min Act: -0.0005

Data Index: 711920 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0031. Min Act: -0.0006

Data Index: 1297265 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0031. Min Act: -0.0005

Data Index: 597951 (C4 (Web Text))

Max Activating Token Index: 65

Text #9

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0030. Min Act: -0.0005

Data Index: 1458516 (Python Code)

Max Activating Token Index: 7

Text #10

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0030. Min Act: -0.0005

Data Index: 1333559 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0029. Min Act: -0.0005

Data Index: 77550 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0030. Min Act: -0.0006

Data Index: 1070985 (C4 (Web Text))

Max Activating Token Index: 7

Text #13

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0029. Min Act: -0.0005

Data Index: 1033223 (C4 (Web Text))

Max Activating Token Index: 365

Text #14

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0029. Min Act: -0.0006

Data Index: 60603 (C4 (Web Text))

Max Activating Token Index: 191

Text #15

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0030. Min Act: -0.0005

Data Index: 412396 (C4 (Web Text))

Max Activating Token Index: 163

Text #16

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0029. Min Act: -0.0005

Data Index: 278470 (C4 (Web Text))

Max Activating Token Index: 151

Text #17

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0029. Min Act: -0.0006

Data Index: 660957 (C4 (Web Text))

Max Activating Token Index: 227

Text #18

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0028. Min Act: -0.0005

Data Index: 806589 (C4 (Web Text))

Max Activating Token Index: 295

Text #19

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0028. Min Act: -0.0005

Data Index: 730127 (C4 (Web Text))

Max Activating Token Index: 272