Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 470 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0166. Min Act: -0.0004

Data Index: 857233 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0162. Min Act: -0.0004

Data Index: 684193 (C4 (Web Text))

Max Activating Token Index: 668

Text #2

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0138. Min Act: -0.0004

Data Index: 1295872 (C4 (Web Text))

Max Activating Token Index: 131

Text #3

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0140. Min Act: -0.0004

Data Index: 43196 (C4 (Web Text))

Max Activating Token Index: 758

Text #4

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0141. Min Act: -0.0004

Data Index: 780934 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0132. Min Act: -0.0004

Data Index: 819394 (C4 (Web Text))

Max Activating Token Index: 641

Text #6

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0131. Min Act: -0.0004

Data Index: 316351 (C4 (Web Text))

Max Activating Token Index: 311

Text #7

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0129. Min Act: -0.0004

Data Index: 764837 (C4 (Web Text))

Max Activating Token Index: 169

Text #8

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0128. Min Act: -0.0004

Data Index: 1056288 (C4 (Web Text))

Max Activating Token Index: 457

Text #9

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0125. Min Act: -0.0004

Data Index: 50360 (C4 (Web Text))

Max Activating Token Index: 824

Text #10

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0129. Min Act: -0.0004

Data Index: 954264 (C4 (Web Text))

Max Activating Token Index: 129

Text #11

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0129. Min Act: -0.0004

Data Index: 873082 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0126. Min Act: -0.0004

Data Index: 372011 (C4 (Web Text))

Max Activating Token Index: 1006

Text #13

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0117. Min Act: -0.0004

Data Index: 331300 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0118. Min Act: -0.0004

Data Index: 1338939 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0114. Min Act: -0.0004

Data Index: 1198879 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0129. Min Act: -0.0004

Data Index: 1056467 (C4 (Web Text))

Max Activating Token Index: 225

Text #17

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0134. Min Act: -0.0004

Data Index: 203170 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0123. Min Act: -0.0004

Data Index: 548405 (C4 (Web Text))

Max Activating Token Index: 58

Text #19

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0135. Min Act: -0.0004

Data Index: 160606 (C4 (Web Text))

Max Activating Token Index: 194