Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2763 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0159. Min Act: -0.0003

Data Index: 721376 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0157. Min Act: -0.0003

Data Index: 361479 (C4 (Web Text))

Max Activating Token Index: 994

Text #2

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0154. Min Act: -0.0003

Data Index: 215436 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0149. Min Act: -0.0003

Data Index: 172074 (C4 (Web Text))

Max Activating Token Index: 961

Text #4

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0140. Min Act: -0.0003

Data Index: 296834 (C4 (Web Text))

Max Activating Token Index: 132

Text #5

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0133. Min Act: -0.0003

Data Index: 412995 (C4 (Web Text))

Max Activating Token Index: 202

Text #6

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0131. Min Act: -0.0003

Data Index: 456132 (C4 (Web Text))

Max Activating Token Index: 657

Text #7

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0130. Min Act: -0.0003

Data Index: 65994 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0130. Min Act: -0.0003

Data Index: 1267178 (C4 (Web Text))

Max Activating Token Index: 302

Text #9

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0125. Min Act: -0.0003

Data Index: 19517 (C4 (Web Text))

Max Activating Token Index: 358

Text #10

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0125. Min Act: -0.0003

Data Index: 264031 (C4 (Web Text))

Max Activating Token Index: 981

Text #11

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0127. Min Act: -0.0003

Data Index: 850550 (C4 (Web Text))

Max Activating Token Index: 947

Text #12

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0124. Min Act: -0.0002

Data Index: 1486027 (Python Code)

Max Activating Token Index: 115

Text #13

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0121. Min Act: -0.0003

Data Index: 938252 (C4 (Web Text))

Max Activating Token Index: 547

Text #14

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0122. Min Act: -0.0003

Data Index: 1035499 (C4 (Web Text))

Max Activating Token Index: 645

Text #15

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0121. Min Act: -0.0003

Data Index: 612242 (C4 (Web Text))

Max Activating Token Index: 213

Text #16

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0121. Min Act: -0.0003

Data Index: 272150 (C4 (Web Text))

Max Activating Token Index: 662

Text #17

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0120. Min Act: -0.0002

Data Index: 1537861 (Python Code)

Max Activating Token Index: 210

Text #18

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0120. Min Act: -0.0002

Data Index: 1457216 (Python Code)

Max Activating Token Index: 66

Text #19

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0119. Min Act: -0.0003

Data Index: 331283 (C4 (Web Text))

Max Activating Token Index: 686