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

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

Neuron 4099 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: 0.0070. Min Range: -0.0070

Max Act: 0.0070. Min Act: -0.0002

Data Index: 1382997 (Python Code)

Max Activating Token Index: 699

Text #1

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0068. Min Act: -0.0002

Data Index: 632376 (C4 (Web Text))

Max Activating Token Index: 269

Text #2

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0069. Min Act: -0.0002

Data Index: 1204190 (C4 (Web Text))

Max Activating Token Index: 157

Text #3

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0067. Min Act: -0.0002

Data Index: 999894 (C4 (Web Text))

Max Activating Token Index: 367

Text #4

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0067. Min Act: -0.0002

Data Index: 835794 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0066. Min Act: -0.0002

Data Index: 346233 (C4 (Web Text))

Max Activating Token Index: 18

Text #6

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0067. Min Act: -0.0002

Data Index: 1205609 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0066. Min Act: -0.0002

Data Index: 1125950 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0066. Min Act: -0.0002

Data Index: 1026328 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0065. Min Act: -0.0002

Data Index: 1619366 (Python Code)

Max Activating Token Index: 350

Text #10

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0065. Min Act: -0.0002

Data Index: 1458017 (Python Code)

Max Activating Token Index: 21

Text #11

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0063. Min Act: -0.0002

Data Index: 575827 (C4 (Web Text))

Max Activating Token Index: 243

Text #12

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0064. Min Act: -0.0002

Data Index: 388555 (C4 (Web Text))

Max Activating Token Index: 141

Text #13

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0063. Min Act: -0.0001

Data Index: 844173 (C4 (Web Text))

Max Activating Token Index: 18

Text #14

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0063. Min Act: -0.0002

Data Index: 1452741 (Python Code)

Max Activating Token Index: 147

Text #15

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0063. Min Act: -0.0002

Data Index: 1638985 (Python Code)

Max Activating Token Index: 137

Text #16

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0064. Min Act: -0.0002

Data Index: 764879 (C4 (Web Text))

Max Activating Token Index: 64

Text #17

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0063. Min Act: -0.0002

Data Index: 625407 (C4 (Web Text))

Max Activating Token Index: 1005

Text #18

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0062. Min Act: -0.0002

Data Index: 210694 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0062. Min Act: -0.0002

Data Index: 830275 (C4 (Web Text))

Max Activating Token Index: 665