Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 623 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0064. Min Act: -0.0002

Data Index: 111178 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0057. Min Act: -0.0002

Data Index: 528468 (C4 (Web Text))

Max Activating Token Index: 199

Text #2

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0051. Min Act: -0.0003

Data Index: 1029715 (C4 (Web Text))

Max Activating Token Index: 41

Text #3

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0036. Min Act: -0.0002

Data Index: 635141 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0036. Min Act: -0.0002

Data Index: 463298 (C4 (Web Text))

Max Activating Token Index: 249

Text #5

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0032. Min Act: -0.0002

Data Index: 1178646 (C4 (Web Text))

Max Activating Token Index: 281

Text #6

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0033. Min Act: -0.0002

Data Index: 873046 (C4 (Web Text))

Max Activating Token Index: 184

Text #7

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0032. Min Act: -0.0002

Data Index: 342649 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0030. Min Act: -0.0002

Data Index: 1119592 (C4 (Web Text))

Max Activating Token Index: 17

Text #9

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0028. Min Act: -0.0002

Data Index: 79630 (C4 (Web Text))

Max Activating Token Index: 362

Text #10

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0028. Min Act: -0.0002

Data Index: 409459 (C4 (Web Text))

Max Activating Token Index: 669

Text #11

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0027. Min Act: -0.0002

Data Index: 321145 (C4 (Web Text))

Max Activating Token Index: 258

Text #12

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0026. Min Act: -0.0002

Data Index: 114774 (C4 (Web Text))

Max Activating Token Index: 132

Text #13

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0026. Min Act: -0.0002

Data Index: 589327 (C4 (Web Text))

Max Activating Token Index: 143

Text #14

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0025. Min Act: -0.0003

Data Index: 328995 (C4 (Web Text))

Max Activating Token Index: 804

Text #15

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0026. Min Act: -0.0002

Data Index: 1194517 (C4 (Web Text))

Max Activating Token Index: 638

Text #16

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0026. Min Act: -0.0002

Data Index: 907815 (C4 (Web Text))

Max Activating Token Index: 187

Text #17

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0026. Min Act: -0.0002

Data Index: 1247535 (C4 (Web Text))

Max Activating Token Index: 148

Text #18

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0025. Min Act: -0.0002

Data Index: 1024358 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0023. Min Act: -0.0002

Data Index: 622602 (C4 (Web Text))

Max Activating Token Index: 547