Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0193. Min Act: -0.0003

Data Index: 1216585 (C4 (Web Text))

Max Activating Token Index: 591

Text #1

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0173. Min Act: -0.0003

Data Index: 160897 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0170. Min Act: -0.0003

Data Index: 116059 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0167. Min Act: -0.0003

Data Index: 536026 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0134. Min Act: -0.0003

Data Index: 528240 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0125. Min Act: -0.0003

Data Index: 799886 (C4 (Web Text))

Max Activating Token Index: 702

Text #6

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0130. Min Act: -0.0003

Data Index: 766241 (C4 (Web Text))

Max Activating Token Index: 887

Text #7

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0125. Min Act: -0.0003

Data Index: 444158 (C4 (Web Text))

Max Activating Token Index: 600

Text #8

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0129. Min Act: -0.0003

Data Index: 1045565 (C4 (Web Text))

Max Activating Token Index: 961

Text #9

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0120. Min Act: -0.0003

Data Index: 120692 (C4 (Web Text))

Max Activating Token Index: 660

Text #10

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0134. Min Act: -0.0003

Data Index: 333592 (C4 (Web Text))

Max Activating Token Index: 790

Text #11

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0123. Min Act: -0.0003

Data Index: 802688 (C4 (Web Text))

Max Activating Token Index: 790

Text #12

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0125. Min Act: -0.0003

Data Index: 1172274 (C4 (Web Text))

Max Activating Token Index: 83

Text #13

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0154. Min Act: -0.0003

Data Index: 580264 (C4 (Web Text))

Max Activating Token Index: 842

Text #14

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0139. Min Act: -0.0003

Data Index: 366550 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0137. Min Act: -0.0003

Data Index: 910662 (C4 (Web Text))

Max Activating Token Index: 231

Text #16

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0123. Min Act: -0.0004

Data Index: 59564 (C4 (Web Text))

Max Activating Token Index: 845

Text #17

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0127. Min Act: -0.0003

Data Index: 170053 (C4 (Web Text))

Max Activating Token Index: 758

Text #18

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0129. Min Act: -0.0003

Data Index: 1446833 (Python Code)

Max Activating Token Index: 771

Text #19

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0144. Min Act: -0.0003

Data Index: 66606 (C4 (Web Text))

Max Activating Token Index: 85