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

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

Neuron 3655 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: 0.0072. Min Range: -0.0072

Max Act: 0.0072. Min Act: -0.0002

Data Index: 1437454 (Python Code)

Max Activating Token Index: 23

Text #1

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0070. Min Act: -0.0002

Data Index: 1416299 (Python Code)

Max Activating Token Index: 8

Text #2

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0068. Min Act: -0.0003

Data Index: 169354 (C4 (Web Text))

Max Activating Token Index: 82

Text #3

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0068. Min Act: -0.0003

Data Index: 1166007 (C4 (Web Text))

Max Activating Token Index: 671

Text #4

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0066. Min Act: -0.0003

Data Index: 379001 (C4 (Web Text))

Max Activating Token Index: 48

Text #5

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0066. Min Act: -0.0003

Data Index: 619125 (C4 (Web Text))

Max Activating Token Index: 423

Text #6

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0065. Min Act: -0.0003

Data Index: 216934 (C4 (Web Text))

Max Activating Token Index: 25

Text #7

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0066. Min Act: -0.0003

Data Index: 231270 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0065. Min Act: -0.0003

Data Index: 331276 (C4 (Web Text))

Max Activating Token Index: 7

Text #9

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0065. Min Act: -0.0003

Data Index: 823573 (C4 (Web Text))

Max Activating Token Index: 666

Text #10

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0065. Min Act: -0.0003

Data Index: 974399 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0065. Min Act: -0.0003

Data Index: 575947 (C4 (Web Text))

Max Activating Token Index: 576

Text #12

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0064. Min Act: -0.0003

Data Index: 634444 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0063. Min Act: -0.0003

Data Index: 1283340 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0063. Min Act: -0.0002

Data Index: 1525505 (Python Code)

Max Activating Token Index: 14

Text #15

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0063. Min Act: -0.0003

Data Index: 904275 (C4 (Web Text))

Max Activating Token Index: 147

Text #16

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0063. Min Act: -0.0003

Data Index: 1069431 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0063. Min Act: -0.0003

Data Index: 759701 (C4 (Web Text))

Max Activating Token Index: 366

Text #18

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0063. Min Act: -0.0003

Data Index: 584227 (C4 (Web Text))

Max Activating Token Index: 592

Text #19

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0063. Min Act: -0.0003

Data Index: 1133361 (C4 (Web Text))

Max Activating Token Index: 285