Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 57 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0180. Min Act: -0.0006

Data Index: 1226842 (C4 (Web Text))

Max Activating Token Index: 649

Text #1

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0135. Min Act: -0.0006

Data Index: 398022 (C4 (Web Text))

Max Activating Token Index: 93

Text #2

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0114. Min Act: -0.0006

Data Index: 608358 (C4 (Web Text))

Max Activating Token Index: 841

Text #3

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0144. Min Act: -0.0006

Data Index: 678863 (C4 (Web Text))

Max Activating Token Index: 765

Text #4

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0133. Min Act: -0.0006

Data Index: 1126544 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0117. Min Act: -0.0006

Data Index: 924207 (C4 (Web Text))

Max Activating Token Index: 190

Text #6

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0116. Min Act: -0.0006

Data Index: 779945 (C4 (Web Text))

Max Activating Token Index: 873

Text #7

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0110. Min Act: -0.0006

Data Index: 187428 (C4 (Web Text))

Max Activating Token Index: 263

Text #8

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0103. Min Act: -0.0006

Data Index: 618334 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0098. Min Act: -0.0006

Data Index: 429785 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0101. Min Act: -0.0006

Data Index: 1282146 (C4 (Web Text))

Max Activating Token Index: 839

Text #11

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0105. Min Act: -0.0006

Data Index: 1062166 (C4 (Web Text))

Max Activating Token Index: 787

Text #12

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0095. Min Act: -0.0006

Data Index: 624435 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0097. Min Act: -0.0006

Data Index: 450780 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0097. Min Act: -0.0006

Data Index: 1174965 (C4 (Web Text))

Max Activating Token Index: 361

Text #15

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0095. Min Act: -0.0006

Data Index: 375810 (C4 (Web Text))

Max Activating Token Index: 414

Text #16

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0090. Min Act: -0.0006

Data Index: 1233284 (C4 (Web Text))

Max Activating Token Index: 650

Text #17

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0093. Min Act: -0.0006

Data Index: 1329870 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0094. Min Act: -0.0006

Data Index: 511123 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0091. Min Act: -0.0006

Data Index: 774401 (C4 (Web Text))

Max Activating Token Index: 545