Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1985 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0044. Min Act: -0.0006

Data Index: 492015 (C4 (Web Text))

Max Activating Token Index: 230

Text #1

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0043. Min Act: -0.0006

Data Index: 615640 (C4 (Web Text))

Max Activating Token Index: 208

Text #2

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0041. Min Act: -0.0006

Data Index: 382034 (C4 (Web Text))

Max Activating Token Index: 4

Text #3

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0040. Min Act: -0.0006

Data Index: 134013 (C4 (Web Text))

Max Activating Token Index: 3

Text #4

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0040. Min Act: -0.0006

Data Index: 426442 (C4 (Web Text))

Max Activating Token Index: 176

Text #5

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0039. Min Act: -0.0006

Data Index: 120185 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0039. Min Act: -0.0006

Data Index: 1168530 (C4 (Web Text))

Max Activating Token Index: 275

Text #7

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0039. Min Act: -0.0006

Data Index: 904475 (C4 (Web Text))

Max Activating Token Index: 536

Text #8

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0038. Min Act: -0.0006

Data Index: 167118 (C4 (Web Text))

Max Activating Token Index: 550

Text #9

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0039. Min Act: -0.0006

Data Index: 198597 (C4 (Web Text))

Max Activating Token Index: 116

Text #10

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0039. Min Act: -0.0006

Data Index: 678578 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0037. Min Act: -0.0006

Data Index: 335539 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0038. Min Act: -0.0006

Data Index: 125041 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0038. Min Act: -0.0006

Data Index: 1294550 (C4 (Web Text))

Max Activating Token Index: 869

Text #14

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0038. Min Act: -0.0006

Data Index: 91057 (C4 (Web Text))

Max Activating Token Index: 650

Text #15

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0037. Min Act: -0.0006

Data Index: 103002 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0037. Min Act: -0.0006

Data Index: 1038548 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0037. Min Act: -0.0006

Data Index: 394137 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0038. Min Act: -0.0006

Data Index: 1240263 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0037. Min Act: -0.0006

Data Index: 947684 (C4 (Web Text))

Max Activating Token Index: 551