Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 331 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0039. Min Act: -0.0005

Data Index: 17718 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0038. Min Act: -0.0006

Data Index: 228315 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0035. Min Act: -0.0005

Data Index: 1482670 (Python Code)

Max Activating Token Index: 213

Text #3

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0035. Min Act: -0.0005

Data Index: 1483422 (Python Code)

Max Activating Token Index: 255

Text #4

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0035. Min Act: -0.0005

Data Index: 1028476 (C4 (Web Text))

Max Activating Token Index: 276

Text #5

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0035. Min Act: -0.0005

Data Index: 1353201 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0033. Min Act: -0.0005

Data Index: 1621884 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0033. Min Act: -0.0005

Data Index: 645764 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0033. Min Act: -0.0005

Data Index: 1637329 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0033. Min Act: -0.0005

Data Index: 782451 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0032. Min Act: -0.0005

Data Index: 1365252 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0032. Min Act: -0.0006

Data Index: 1001436 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0032. Min Act: -0.0005

Data Index: 608763 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0032. Min Act: -0.0005

Data Index: 1564357 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0032. Min Act: -0.0005

Data Index: 1425883 (Python Code)

Max Activating Token Index: 301

Text #15

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0032. Min Act: -0.0005

Data Index: 245979 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0031. Min Act: -0.0005

Data Index: 635551 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0031. Min Act: -0.0005

Data Index: 691798 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0031. Min Act: -0.0005

Data Index: 567514 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0031. Min Act: -0.0005

Data Index: 525856 (C4 (Web Text))

Max Activating Token Index: 1023