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

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

Neuron 953 in Layer 1

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: 0.0171. Min Range: -0.0171

Max Act: 0.0171. Min Act: -0.0002

Data Index: 1110324 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0141. Min Act: -0.0002

Data Index: 230722 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0135. Min Act: -0.0002

Data Index: 776564 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0136. Min Act: -0.0003

Data Index: 539940 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0134. Min Act: -0.0002

Data Index: 772518 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0125. Min Act: -0.0003

Data Index: 203849 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0121. Min Act: -0.0002

Data Index: 1443852 (Python Code)

Max Activating Token Index: 710

Text #7

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0125. Min Act: -0.0002

Data Index: 1259258 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0119. Min Act: -0.0002

Data Index: 144975 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0118. Min Act: -0.0002

Data Index: 664123 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0120. Min Act: -0.0002

Data Index: 140168 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0115. Min Act: -0.0002

Data Index: 841206 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0112. Min Act: -0.0002

Data Index: 49426 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0112. Min Act: -0.0002

Data Index: 303172 (C4 (Web Text))

Max Activating Token Index: 833

Text #14

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0115. Min Act: -0.0002

Data Index: 515385 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0111. Min Act: -0.0002

Data Index: 1588458 (Python Code)

Max Activating Token Index: 760

Text #16

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0111. Min Act: -0.0002

Data Index: 971568 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0107. Min Act: -0.0002

Data Index: 1481239 (Python Code)

Max Activating Token Index: 843

Text #18

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0107. Min Act: -0.0002

Data Index: 1234356 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0106. Min Act: -0.0002

Data Index: 1403388 (Python Code)

Max Activating Token Index: 491