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

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

Neuron 2521 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0110. Min Act: -0.0003

Data Index: 890920 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0102. Min Act: -0.0003

Data Index: 146696 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0086. Min Act: -0.0003

Data Index: 83886 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0068. Min Act: -0.0003

Data Index: 1187131 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0063. Min Act: -0.0003

Data Index: 1304288 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0066. Min Act: -0.0003

Data Index: 181047 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0068. Min Act: -0.0003

Data Index: 4213 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0056. Min Act: -0.0004

Data Index: 1561154 (Python Code)

Max Activating Token Index: 810

Text #8

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0074. Min Act: -0.0003

Data Index: 862456 (C4 (Web Text))

Max Activating Token Index: 611

Text #9

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0059. Min Act: -0.0003

Data Index: 168382 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0059. Min Act: -0.0003

Data Index: 868742 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0052. Min Act: -0.0003

Data Index: 836230 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0064. Min Act: -0.0003

Data Index: 822153 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0053. Min Act: -0.0004

Data Index: 1558958 (Python Code)

Max Activating Token Index: 827

Text #14

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0059. Min Act: -0.0003

Data Index: 1079690 (C4 (Web Text))

Max Activating Token Index: 388

Text #15

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0054. Min Act: -0.0003

Data Index: 751479 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0057. Min Act: -0.0003

Data Index: 1233556 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0057. Min Act: -0.0003

Data Index: 113351 (C4 (Web Text))

Max Activating Token Index: 652

Text #18

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0056. Min Act: -0.0003

Data Index: 15728 (C4 (Web Text))

Max Activating Token Index: 287

Text #19

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0058. Min Act: -0.0003

Data Index: 1119040 (C4 (Web Text))

Max Activating Token Index: 473