Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4824 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0178. Min Act: -0.0002

Data Index: 1649302 (Python Code)

Max Activating Token Index: 552

Text #1

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0110. Min Act: -0.0002

Data Index: 1656427 (Python Code)

Max Activating Token Index: 373

Text #2

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0104. Min Act: -0.0002

Data Index: 719258 (C4 (Web Text))

Max Activating Token Index: 464

Text #3

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0102. Min Act: -0.0002

Data Index: 956768 (C4 (Web Text))

Max Activating Token Index: 852

Text #4

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0098. Min Act: -0.0002

Data Index: 208309 (C4 (Web Text))

Max Activating Token Index: 381

Text #5

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0113. Min Act: -0.0002

Data Index: 1362900 (Python Code)

Max Activating Token Index: 276

Text #6

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0100. Min Act: -0.0002

Data Index: 1225276 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0116. Min Act: -0.0002

Data Index: 580164 (C4 (Web Text))

Max Activating Token Index: 800

Text #8

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0105. Min Act: -0.0002

Data Index: 882971 (C4 (Web Text))

Max Activating Token Index: 632

Text #9

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0098. Min Act: -0.0002

Data Index: 1611660 (Python Code)

Max Activating Token Index: 269

Text #10

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0092. Min Act: -0.0002

Data Index: 1655339 (Python Code)

Max Activating Token Index: 870

Text #11

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0098. Min Act: -0.0002

Data Index: 941097 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0092. Min Act: -0.0002

Data Index: 1417703 (Python Code)

Max Activating Token Index: 109

Text #13

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0094. Min Act: -0.0002

Data Index: 56763 (C4 (Web Text))

Max Activating Token Index: 295

Text #14

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0091. Min Act: -0.0002

Data Index: 942063 (C4 (Web Text))

Max Activating Token Index: 369

Text #15

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0089. Min Act: -0.0002

Data Index: 157534 (C4 (Web Text))

Max Activating Token Index: 877

Text #16

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0093. Min Act: -0.0002

Data Index: 1427736 (Python Code)

Max Activating Token Index: 123

Text #17

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0089. Min Act: -0.0002

Data Index: 780783 (C4 (Web Text))

Max Activating Token Index: 596

Text #18

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0085. Min Act: -0.0002

Data Index: 265103 (C4 (Web Text))

Max Activating Token Index: 387

Text #19

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0091. Min Act: -0.0002

Data Index: 1458038 (Python Code)

Max Activating Token Index: 531