Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 13 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0069. Min Act: -0.0003

Data Index: 1403754 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0065. Min Act: -0.0003

Data Index: 995707 (C4 (Web Text))

Max Activating Token Index: 384

Text #2

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0063. Min Act: -0.0003

Data Index: 847411 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0062. Min Act: -0.0004

Data Index: 465530 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0061. Min Act: -0.0003

Data Index: 959536 (C4 (Web Text))

Max Activating Token Index: 716

Text #5

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0060. Min Act: -0.0003

Data Index: 1176788 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0059. Min Act: -0.0003

Data Index: 1410116 (Python Code)

Max Activating Token Index: 408

Text #7

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0058. Min Act: -0.0004

Data Index: 315171 (C4 (Web Text))

Max Activating Token Index: 114

Text #8

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0057. Min Act: -0.0003

Data Index: 1132006 (C4 (Web Text))

Max Activating Token Index: 559

Text #9

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0058. Min Act: -0.0003

Data Index: 1511671 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0057. Min Act: -0.0003

Data Index: 1638836 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0056. Min Act: -0.0003

Data Index: 353869 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0056. Min Act: -0.0003

Data Index: 1232190 (C4 (Web Text))

Max Activating Token Index: 668

Text #13

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0056. Min Act: -0.0003

Data Index: 272417 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0055. Min Act: -0.0004

Data Index: 315215 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0055. Min Act: -0.0004

Data Index: 661579 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0054. Min Act: -0.0003

Data Index: 2605 (C4 (Web Text))

Max Activating Token Index: 840

Text #17

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0055. Min Act: -0.0003

Data Index: 1498396 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0054. Min Act: -0.0004

Data Index: 1420862 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0053. Min Act: -0.0004

Data Index: 1245515 (C4 (Web Text))

Max Activating Token Index: 1023