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

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

Neuron 840 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: 0.0314. Min Range: -0.0314

Max Act: 0.0314. Min Act: -0.0005

Data Index: 49443 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0308. Min Act: -0.0005

Data Index: 489101 (C4 (Web Text))

Max Activating Token Index: 669

Text #2

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0312. Min Act: -0.0005

Data Index: 180681 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0312. Min Act: -0.0006

Data Index: 40497 (C4 (Web Text))

Max Activating Token Index: 3

Text #4

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0312. Min Act: -0.0005

Data Index: 518882 (C4 (Web Text))

Max Activating Token Index: 3

Text #5

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0312. Min Act: -0.0005

Data Index: 378211 (C4 (Web Text))

Max Activating Token Index: 3

Text #6

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0312. Min Act: -0.0005

Data Index: 71029 (C4 (Web Text))

Max Activating Token Index: 3

Text #7

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0312. Min Act: -0.0005

Data Index: 299806 (C4 (Web Text))

Max Activating Token Index: 3

Text #8

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0312. Min Act: -0.0005

Data Index: 88175 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0312. Min Act: -0.0006

Data Index: 241537 (C4 (Web Text))

Max Activating Token Index: 3

Text #10

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0312. Min Act: -0.0005

Data Index: 345206 (C4 (Web Text))

Max Activating Token Index: 3

Text #11

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0312. Min Act: -0.0005

Data Index: 387848 (C4 (Web Text))

Max Activating Token Index: 3

Text #12

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0312. Min Act: -0.0005

Data Index: 364718 (C4 (Web Text))

Max Activating Token Index: 3

Text #13

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0312. Min Act: -0.0005

Data Index: 478177 (C4 (Web Text))

Max Activating Token Index: 3

Text #14

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0312. Min Act: -0.0005

Data Index: 297255 (C4 (Web Text))

Max Activating Token Index: 3

Text #15

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0312. Min Act: -0.0005

Data Index: 88937 (C4 (Web Text))

Max Activating Token Index: 3

Text #16

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0312. Min Act: -0.0005

Data Index: 353569 (C4 (Web Text))

Max Activating Token Index: 3

Text #17

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0312. Min Act: -0.0005

Data Index: 159080 (C4 (Web Text))

Max Activating Token Index: 3

Text #18

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0312. Min Act: -0.0006

Data Index: 521129 (C4 (Web Text))

Max Activating Token Index: 3

Text #19

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0312. Min Act: -0.0005

Data Index: 445607 (C4 (Web Text))

Max Activating Token Index: 3