Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2086 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0158. Min Act: -0.0001

Data Index: 438250 (C4 (Web Text))

Max Activating Token Index: 367

Text #1

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0135. Min Act: -0.0001

Data Index: 551176 (C4 (Web Text))

Max Activating Token Index: 608

Text #2

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0132. Min Act: -0.0001

Data Index: 395829 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0129. Min Act: -0.0001

Data Index: 989589 (C4 (Web Text))

Max Activating Token Index: 462

Text #4

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0129. Min Act: -0.0001

Data Index: 70264 (C4 (Web Text))

Max Activating Token Index: 931

Text #5

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0127. Min Act: -0.0001

Data Index: 762838 (C4 (Web Text))

Max Activating Token Index: 873

Text #6

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0129. Min Act: -0.0001

Data Index: 1325676 (C4 (Web Text))

Max Activating Token Index: 817

Text #7

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0126. Min Act: -0.0001

Data Index: 830937 (C4 (Web Text))

Max Activating Token Index: 881

Text #8

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0124. Min Act: -0.0002

Data Index: 1567385 (Python Code)

Max Activating Token Index: 21

Text #9

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0122. Min Act: -0.0001

Data Index: 624919 (C4 (Web Text))

Max Activating Token Index: 160

Text #10

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0119. Min Act: -0.0001

Data Index: 1272049 (C4 (Web Text))

Max Activating Token Index: 212

Text #11

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0119. Min Act: -0.0001

Data Index: 561025 (C4 (Web Text))

Max Activating Token Index: 907

Text #12

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0120. Min Act: -0.0001

Data Index: 1016019 (C4 (Web Text))

Max Activating Token Index: 718

Text #13

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0119. Min Act: -0.0001

Data Index: 46117 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0119. Min Act: -0.0001

Data Index: 1503902 (Python Code)

Max Activating Token Index: 173

Text #15

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0116. Min Act: -0.0001

Data Index: 1200655 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0117. Min Act: -0.0001

Data Index: 127538 (C4 (Web Text))

Max Activating Token Index: 506

Text #17

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0115. Min Act: -0.0001

Data Index: 1497012 (Python Code)

Max Activating Token Index: 24

Text #18

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0113. Min Act: -0.0001

Data Index: 24864 (C4 (Web Text))

Max Activating Token Index: 663

Text #19

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0114. Min Act: -0.0001

Data Index: 672861 (C4 (Web Text))

Max Activating Token Index: 356