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

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

Neuron 4604 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: 0.0069. Min Range: -0.0069

Max Act: 0.0069. Min Act: -0.0002

Data Index: 448098 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0069. Min Act: -0.0002

Data Index: 1209408 (C4 (Web Text))

Max Activating Token Index: 66

Text #2

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0069. Min Act: -0.0002

Data Index: 782248 (C4 (Web Text))

Max Activating Token Index: 65

Text #3

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0069. Min Act: -0.0002

Data Index: 1118670 (C4 (Web Text))

Max Activating Token Index: 248

Text #4

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0069. Min Act: -0.0002

Data Index: 1183658 (C4 (Web Text))

Max Activating Token Index: 265

Text #5

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0068. Min Act: -0.0002

Data Index: 1132223 (C4 (Web Text))

Max Activating Token Index: 292

Text #6

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0068. Min Act: -0.0002

Data Index: 825916 (C4 (Web Text))

Max Activating Token Index: 191

Text #7

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0068. Min Act: -0.0002

Data Index: 1042153 (C4 (Web Text))

Max Activating Token Index: 391

Text #8

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0068. Min Act: -0.0002

Data Index: 960988 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0067. Min Act: -0.0002

Data Index: 156581 (C4 (Web Text))

Max Activating Token Index: 15

Text #10

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0066. Min Act: -0.0002

Data Index: 1122314 (C4 (Web Text))

Max Activating Token Index: 494

Text #11

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0066. Min Act: -0.0002

Data Index: 336184 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0067. Min Act: -0.0002

Data Index: 562789 (C4 (Web Text))

Max Activating Token Index: 109

Text #13

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0066. Min Act: -0.0002

Data Index: 991608 (C4 (Web Text))

Max Activating Token Index: 143

Text #14

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0067. Min Act: -0.0002

Data Index: 107747 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0065. Min Act: -0.0002

Data Index: 46878 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0067. Min Act: -0.0002

Data Index: 88151 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0066. Min Act: -0.0002

Data Index: 20201 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0066. Min Act: -0.0002

Data Index: 246033 (C4 (Web Text))

Max Activating Token Index: 165

Text #19

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0066. Min Act: -0.0002

Data Index: 1294995 (C4 (Web Text))

Max Activating Token Index: 50