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

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

Neuron 2095 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: 0.0075. Min Range: -0.0075

Max Act: 0.0075. Min Act: -0.0003

Data Index: 387169 (C4 (Web Text))

Max Activating Token Index: 746

Text #1

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0059. Min Act: -0.0003

Data Index: 1192217 (C4 (Web Text))

Max Activating Token Index: 521

Text #2

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0057. Min Act: -0.0002

Data Index: 1332221 (C4 (Web Text))

Max Activating Token Index: 197

Text #3

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0056. Min Act: -0.0003

Data Index: 1026730 (C4 (Web Text))

Max Activating Token Index: 860

Text #4

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0056. Min Act: -0.0002

Data Index: 793584 (C4 (Web Text))

Max Activating Token Index: 851

Text #5

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0054. Min Act: -0.0002

Data Index: 413175 (C4 (Web Text))

Max Activating Token Index: 705

Text #6

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0052. Min Act: -0.0002

Data Index: 963110 (C4 (Web Text))

Max Activating Token Index: 749

Text #7

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0051. Min Act: -0.0002

Data Index: 478990 (C4 (Web Text))

Max Activating Token Index: 800

Text #8

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0051. Min Act: -0.0003

Data Index: 1036564 (C4 (Web Text))

Max Activating Token Index: 486

Text #9

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0050. Min Act: -0.0002

Data Index: 1168493 (C4 (Web Text))

Max Activating Token Index: 960

Text #10

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0050. Min Act: -0.0003

Data Index: 633569 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0048. Min Act: -0.0002

Data Index: 896303 (C4 (Web Text))

Max Activating Token Index: 853

Text #12

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0049. Min Act: -0.0002

Data Index: 752390 (C4 (Web Text))

Max Activating Token Index: 596

Text #13

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0049. Min Act: -0.0002

Data Index: 1008978 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0049. Min Act: -0.0002

Data Index: 327115 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0048. Min Act: -0.0002

Data Index: 269798 (C4 (Web Text))

Max Activating Token Index: 270

Text #16

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0048. Min Act: -0.0002

Data Index: 724137 (C4 (Web Text))

Max Activating Token Index: 922

Text #17

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0047. Min Act: -0.0002

Data Index: 1318747 (C4 (Web Text))

Max Activating Token Index: 216

Text #18

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0047. Min Act: -0.0002

Data Index: 538968 (C4 (Web Text))

Max Activating Token Index: 214

Text #19

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0047. Min Act: -0.0002

Data Index: 1239932 (C4 (Web Text))

Max Activating Token Index: 774