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

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

Neuron 229 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0212. Min Act: -0.0004

Data Index: 1521267 (Python Code)

Max Activating Token Index: 76

Text #1

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0169. Min Act: -0.0005

Data Index: 1409000 (Python Code)

Max Activating Token Index: 34

Text #2

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0158. Min Act: -0.0005

Data Index: 1383149 (Python Code)

Max Activating Token Index: 33

Text #3

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0147. Min Act: -0.0005

Data Index: 1485623 (Python Code)

Max Activating Token Index: 48

Text #4

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0145. Min Act: -0.0005

Data Index: 813730 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0142. Min Act: -0.0005

Data Index: 1613270 (Python Code)

Max Activating Token Index: 54

Text #6

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0140. Min Act: -0.0005

Data Index: 638199 (C4 (Web Text))

Max Activating Token Index: 57

Text #7

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0140. Min Act: -0.0004

Data Index: 1639193 (Python Code)

Max Activating Token Index: 27

Text #8

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0140. Min Act: -0.0004

Data Index: 1508209 (Python Code)

Max Activating Token Index: 40

Text #9

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0140. Min Act: -0.0005

Data Index: 1036794 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0140. Min Act: -0.0005

Data Index: 1593651 (Python Code)

Max Activating Token Index: 26

Text #11

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0142. Min Act: -0.0005

Data Index: 613420 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0138. Min Act: -0.0005

Data Index: 1380878 (Python Code)

Max Activating Token Index: 29

Text #13

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0139. Min Act: -0.0005

Data Index: 1596454 (Python Code)

Max Activating Token Index: 45

Text #14

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0138. Min Act: -0.0005

Data Index: 1520415 (Python Code)

Max Activating Token Index: 33

Text #15

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0137. Min Act: -0.0005

Data Index: 1601524 (Python Code)

Max Activating Token Index: 30

Text #16

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0141. Min Act: -0.0004

Data Index: 1374528 (Python Code)

Max Activating Token Index: 38

Text #17

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0137. Min Act: -0.0005

Data Index: 1529022 (Python Code)

Max Activating Token Index: 30

Text #18

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0137. Min Act: -0.0005

Data Index: 1451752 (Python Code)

Max Activating Token Index: 33

Text #19

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0136. Min Act: -0.0004

Data Index: 1496837 (Python Code)

Max Activating Token Index: 33