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

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

Neuron 408 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: 0.0130. Min Range: -0.0130

Max Act: 0.0130. Min Act: -0.0005

Data Index: 307297 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0123. Min Act: -0.0005

Data Index: 1298935 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0123. Min Act: -0.0005

Data Index: 127149 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0118. Min Act: -0.0005

Data Index: 1360301 (Python Code)

Max Activating Token Index: 1

Text #4

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0118. Min Act: -0.0005

Data Index: 1360669 (Python Code)

Max Activating Token Index: 1

Text #5

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0118. Min Act: -0.0005

Data Index: 1360318 (Python Code)

Max Activating Token Index: 1

Text #6

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0118. Min Act: -0.0005

Data Index: 1360265 (Python Code)

Max Activating Token Index: 1

Text #7

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0118. Min Act: -0.0005

Data Index: 1360030 (Python Code)

Max Activating Token Index: 1

Text #8

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0118. Min Act: -0.0005

Data Index: 1360336 (Python Code)

Max Activating Token Index: 1

Text #9

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0118. Min Act: -0.0005

Data Index: 1360299 (Python Code)

Max Activating Token Index: 1

Text #10

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0118. Min Act: -0.0005

Data Index: 1360185 (Python Code)

Max Activating Token Index: 1

Text #11

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0118. Min Act: -0.0005

Data Index: 1360467 (Python Code)

Max Activating Token Index: 1

Text #12

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0118. Min Act: -0.0005

Data Index: 1360287 (Python Code)

Max Activating Token Index: 1

Text #13

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0118. Min Act: -0.0004

Data Index: 1359927 (Python Code)

Max Activating Token Index: 1

Text #14

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0118. Min Act: -0.0005

Data Index: 1360648 (Python Code)

Max Activating Token Index: 1

Text #15

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0118. Min Act: -0.0005

Data Index: 1360517 (Python Code)

Max Activating Token Index: 1

Text #16

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0118. Min Act: -0.0005

Data Index: 1360439 (Python Code)

Max Activating Token Index: 1

Text #17

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0118. Min Act: -0.0004

Data Index: 1360143 (Python Code)

Max Activating Token Index: 1

Text #18

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0118. Min Act: -0.0005

Data Index: 1360182 (Python Code)

Max Activating Token Index: 1

Text #19

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0118. Min Act: -0.0005

Data Index: 1360110 (Python Code)

Max Activating Token Index: 1