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

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

Neuron 5281 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2499. Min Act: -0.0001

Data Index: 258685 (C4 (Web Text))

Max Activating Token Index: 329

Text #1

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2569. Min Act: -0.0001

Data Index: 721050 (C4 (Web Text))

Max Activating Token Index: 738

Text #2

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2558. Min Act: -0.0001

Data Index: 875395 (C4 (Web Text))

Max Activating Token Index: 405

Text #3

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2315. Min Act: -0.0001

Data Index: 1240135 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2459. Min Act: -0.0001

Data Index: 572974 (C4 (Web Text))

Max Activating Token Index: 285

Text #5

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2146. Min Act: -0.0001

Data Index: 620386 (C4 (Web Text))

Max Activating Token Index: 288

Text #6

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2356. Min Act: -0.0001

Data Index: 640568 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2035. Min Act: -0.0001

Data Index: 797415 (C4 (Web Text))

Max Activating Token Index: 439

Text #8

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2189. Min Act: -0.0001

Data Index: 1226351 (C4 (Web Text))

Max Activating Token Index: 415

Text #9

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2164. Min Act: -0.0001

Data Index: 883036 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2120. Min Act: -0.0001

Data Index: 9994 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2217. Min Act: -0.0001

Data Index: 143202 (C4 (Web Text))

Max Activating Token Index: 508

Text #12

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2064. Min Act: -0.0001

Data Index: 1198528 (C4 (Web Text))

Max Activating Token Index: 298

Text #13

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.1992. Min Act: -0.0001

Data Index: 898201 (C4 (Web Text))

Max Activating Token Index: 247

Text #14

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2167. Min Act: -0.0001

Data Index: 149914 (C4 (Web Text))

Max Activating Token Index: 220

Text #15

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2021. Min Act: -0.0001

Data Index: 315879 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2021. Min Act: -0.0001

Data Index: 814850 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2098. Min Act: -0.0001

Data Index: 659511 (C4 (Web Text))

Max Activating Token Index: 233

Text #18

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2077. Min Act: -0.0001

Data Index: 1027026 (C4 (Web Text))

Max Activating Token Index: 474

Text #19

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2093. Min Act: -0.0001

Data Index: 1015837 (C4 (Web Text))

Max Activating Token Index: 934