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

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

Neuron 789 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: 0.0043. Min Range: -0.0043

Max Act: 0.0043. Min Act: -0.0003

Data Index: 1072336 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0042. Min Act: -0.0003

Data Index: 219760 (C4 (Web Text))

Max Activating Token Index: 262

Text #2

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0042. Min Act: -0.0004

Data Index: 29121 (C4 (Web Text))

Max Activating Token Index: 48

Text #3

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0040. Min Act: -0.0003

Data Index: 38282 (C4 (Web Text))

Max Activating Token Index: 140

Text #4

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0040. Min Act: -0.0003

Data Index: 1025097 (C4 (Web Text))

Max Activating Token Index: 373

Text #5

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0039. Min Act: -0.0004

Data Index: 1270159 (C4 (Web Text))

Max Activating Token Index: 335

Text #6

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0039. Min Act: -0.0003

Data Index: 906029 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0038. Min Act: -0.0003

Data Index: 887637 (C4 (Web Text))

Max Activating Token Index: 372

Text #8

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0038. Min Act: -0.0003

Data Index: 1274097 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0037. Min Act: -0.0003

Data Index: 1370011 (Python Code)

Max Activating Token Index: 570

Text #10

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0037. Min Act: -0.0004

Data Index: 212304 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0037. Min Act: -0.0004

Data Index: 1175779 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0037. Min Act: -0.0003

Data Index: 1449890 (Python Code)

Max Activating Token Index: 386

Text #13

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0037. Min Act: -0.0003

Data Index: 679265 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0037. Min Act: -0.0003

Data Index: 1619913 (Python Code)

Max Activating Token Index: 909

Text #15

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0036. Min Act: -0.0003

Data Index: 1429204 (Python Code)

Max Activating Token Index: 527

Text #16

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0037. Min Act: -0.0003

Data Index: 828453 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0037. Min Act: -0.0004

Data Index: 486625 (C4 (Web Text))

Max Activating Token Index: 382

Text #18

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0037. Min Act: -0.0004

Data Index: 441381 (C4 (Web Text))

Max Activating Token Index: 504

Text #19

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0037. Min Act: -0.0003

Data Index: 718386 (C4 (Web Text))

Max Activating Token Index: 466