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

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

Neuron 4456 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: 0.0135. Min Range: -0.0135

Max Act: 0.0135. Min Act: -0.0002

Data Index: 857164 (C4 (Web Text))

Max Activating Token Index: 928

Text #1

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0132. Min Act: -0.0002

Data Index: 205787 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0130. Min Act: -0.0002

Data Index: 833459 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0129. Min Act: -0.0002

Data Index: 1041578 (C4 (Web Text))

Max Activating Token Index: 970

Text #4

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0126. Min Act: -0.0002

Data Index: 29893 (C4 (Web Text))

Max Activating Token Index: 816

Text #5

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0125. Min Act: -0.0002

Data Index: 590034 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0124. Min Act: -0.0002

Data Index: 179082 (C4 (Web Text))

Max Activating Token Index: 853

Text #7

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0124. Min Act: -0.0002

Data Index: 745681 (C4 (Web Text))

Max Activating Token Index: 849

Text #8

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0123. Min Act: -0.0002

Data Index: 706631 (C4 (Web Text))

Max Activating Token Index: 649

Text #9

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0121. Min Act: -0.0002

Data Index: 424055 (C4 (Web Text))

Max Activating Token Index: 284

Text #10

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0122. Min Act: -0.0002

Data Index: 1212768 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0119. Min Act: -0.0002

Data Index: 608405 (C4 (Web Text))

Max Activating Token Index: 18

Text #12

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0121. Min Act: -0.0002

Data Index: 1028817 (C4 (Web Text))

Max Activating Token Index: 908

Text #13

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0118. Min Act: -0.0002

Data Index: 725302 (C4 (Web Text))

Max Activating Token Index: 501

Text #14

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0123. Min Act: -0.0002

Data Index: 1045568 (C4 (Web Text))

Max Activating Token Index: 324

Text #15

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0123. Min Act: -0.0002

Data Index: 1065701 (C4 (Web Text))

Max Activating Token Index: 907

Text #16

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0119. Min Act: -0.0002

Data Index: 1263822 (C4 (Web Text))

Max Activating Token Index: 849

Text #17

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0119. Min Act: -0.0002

Data Index: 722536 (C4 (Web Text))

Max Activating Token Index: 893

Text #18

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0119. Min Act: -0.0002

Data Index: 654595 (C4 (Web Text))

Max Activating Token Index: 741

Text #19

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0119. Min Act: -0.0002

Data Index: 958125 (C4 (Web Text))

Max Activating Token Index: 17