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

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

Neuron 4826 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0139. Min Act: -0.0002

Data Index: 1102248 (C4 (Web Text))

Max Activating Token Index: 529

Text #1

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0144. Min Act: -0.0003

Data Index: 654821 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0134. Min Act: -0.0003

Data Index: 191635 (C4 (Web Text))

Max Activating Token Index: 378

Text #3

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0130. Min Act: -0.0002

Data Index: 707105 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0129. Min Act: -0.0003

Data Index: 816792 (C4 (Web Text))

Max Activating Token Index: 183

Text #5

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0128. Min Act: -0.0003

Data Index: 697084 (C4 (Web Text))

Max Activating Token Index: 487

Text #6

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0130. Min Act: -0.0002

Data Index: 313893 (C4 (Web Text))

Max Activating Token Index: 619

Text #7

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0132. Min Act: -0.0003

Data Index: 112457 (C4 (Web Text))

Max Activating Token Index: 195

Text #8

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0131. Min Act: -0.0003

Data Index: 1260835 (C4 (Web Text))

Max Activating Token Index: 500

Text #9

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0116. Min Act: -0.0003

Data Index: 327302 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0117. Min Act: -0.0003

Data Index: 63283 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0114. Min Act: -0.0003

Data Index: 935077 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0113. Min Act: -0.0003

Data Index: 770402 (C4 (Web Text))

Max Activating Token Index: 154

Text #13

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0115. Min Act: -0.0003

Data Index: 645918 (C4 (Web Text))

Max Activating Token Index: 746

Text #14

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0120. Min Act: -0.0003

Data Index: 1482938 (Python Code)

Max Activating Token Index: 405

Text #15

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0101. Min Act: -0.0003

Data Index: 520154 (C4 (Web Text))

Max Activating Token Index: 206

Text #16

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0108. Min Act: -0.0003

Data Index: 493930 (C4 (Web Text))

Max Activating Token Index: 619

Text #17

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0111. Min Act: -0.0003

Data Index: 170021 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0105. Min Act: -0.0002

Data Index: 954664 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0112. Min Act: -0.0003

Data Index: 1355490 (C4 (Web Text))

Max Activating Token Index: 173