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

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

Neuron 5066 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0067. Min Act: -0.0002

Data Index: 40896 (C4 (Web Text))

Max Activating Token Index: 126

Text #1

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0066. Min Act: -0.0002

Data Index: 1263726 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0063. Min Act: -0.0002

Data Index: 238389 (C4 (Web Text))

Max Activating Token Index: 146

Text #3

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0062. Min Act: -0.0002

Data Index: 1129417 (C4 (Web Text))

Max Activating Token Index: 712

Text #4

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0061. Min Act: -0.0002

Data Index: 540881 (C4 (Web Text))

Max Activating Token Index: 151

Text #5

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0060. Min Act: -0.0002

Data Index: 232936 (C4 (Web Text))

Max Activating Token Index: 67

Text #6

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0060. Min Act: -0.0002

Data Index: 471167 (C4 (Web Text))

Max Activating Token Index: 360

Text #7

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0059. Min Act: -0.0002

Data Index: 1359513 (C4 (Web Text))

Max Activating Token Index: 497

Text #8

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0058. Min Act: -0.0002

Data Index: 37119 (C4 (Web Text))

Max Activating Token Index: 801

Text #9

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0057. Min Act: -0.0002

Data Index: 3340 (C4 (Web Text))

Max Activating Token Index: 325

Text #10

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0057. Min Act: -0.0002

Data Index: 1157757 (C4 (Web Text))

Max Activating Token Index: 43

Text #11

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0057. Min Act: -0.0002

Data Index: 389829 (C4 (Web Text))

Max Activating Token Index: 164

Text #12

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0057. Min Act: -0.0002

Data Index: 1448284 (Python Code)

Max Activating Token Index: 223

Text #13

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0056. Min Act: -0.0002

Data Index: 649505 (C4 (Web Text))

Max Activating Token Index: 545

Text #14

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0056. Min Act: -0.0002

Data Index: 322878 (C4 (Web Text))

Max Activating Token Index: 326

Text #15

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0056. Min Act: -0.0002

Data Index: 1135487 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0057. Min Act: -0.0002

Data Index: 397269 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0056. Min Act: -0.0002

Data Index: 686569 (C4 (Web Text))

Max Activating Token Index: 652

Text #18

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0056. Min Act: -0.0002

Data Index: 1286187 (C4 (Web Text))

Max Activating Token Index: 781

Text #19

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0057. Min Act: -0.0002

Data Index: 344754 (C4 (Web Text))

Max Activating Token Index: 69