Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 103 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0134. Min Act: -0.0002

Data Index: 965452 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0132. Min Act: -0.0002

Data Index: 648114 (C4 (Web Text))

Max Activating Token Index: 324

Text #2

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0129. Min Act: -0.0002

Data Index: 1270045 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0129. Min Act: -0.0002

Data Index: 951121 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0126. Min Act: -0.0002

Data Index: 1318786 (C4 (Web Text))

Max Activating Token Index: 223

Text #5

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0128. Min Act: -0.0002

Data Index: 1261780 (C4 (Web Text))

Max Activating Token Index: 85

Text #6

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0127. Min Act: -0.0002

Data Index: 225414 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0127. Min Act: -0.0002

Data Index: 72850 (C4 (Web Text))

Max Activating Token Index: 107

Text #8

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0127. Min Act: -0.0002

Data Index: 375427 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0126. Min Act: -0.0002

Data Index: 343154 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0126. Min Act: -0.0002

Data Index: 155048 (C4 (Web Text))

Max Activating Token Index: 258

Text #11

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0126. Min Act: -0.0002

Data Index: 787079 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0126. Min Act: -0.0002

Data Index: 62589 (C4 (Web Text))

Max Activating Token Index: 84

Text #13

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0126. Min Act: -0.0002

Data Index: 127673 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0125. Min Act: -0.0002

Data Index: 396223 (C4 (Web Text))

Max Activating Token Index: 174

Text #15

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0125. Min Act: -0.0002

Data Index: 845006 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0125. Min Act: -0.0002

Data Index: 617149 (C4 (Web Text))

Max Activating Token Index: 29

Text #17

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0127. Min Act: -0.0002

Data Index: 49246 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0124. Min Act: -0.0002

Data Index: 401647 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0124. Min Act: -0.0002

Data Index: 647112 (C4 (Web Text))

Max Activating Token Index: 180