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

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

Neuron 4581 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0138. Min Act: -0.0001

Data Index: 1652750 (Python Code)

Max Activating Token Index: 185

Text #1

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0137. Min Act: -0.0002

Data Index: 1653626 (Python Code)

Max Activating Token Index: 731

Text #2

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0137. Min Act: -0.0002

Data Index: 1612335 (Python Code)

Max Activating Token Index: 333

Text #3

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0133. Min Act: -0.0002

Data Index: 1430077 (Python Code)

Max Activating Token Index: 16

Text #4

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0137. Min Act: -0.0002

Data Index: 1501987 (Python Code)

Max Activating Token Index: 7

Text #5

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0134. Min Act: -0.0001

Data Index: 1390749 (Python Code)

Max Activating Token Index: 11

Text #6

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0134. Min Act: -0.0002

Data Index: 1630269 (Python Code)

Max Activating Token Index: 690

Text #7

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0136. Min Act: -0.0002

Data Index: 1584820 (Python Code)

Max Activating Token Index: 20

Text #8

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0133. Min Act: -0.0002

Data Index: 1381075 (Python Code)

Max Activating Token Index: 12

Text #9

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0132. Min Act: -0.0002

Data Index: 1652698 (Python Code)

Max Activating Token Index: 621

Text #10

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0134. Min Act: -0.0002

Data Index: 1603442 (Python Code)

Max Activating Token Index: 201

Text #11

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0132. Min Act: -0.0002

Data Index: 1397065 (Python Code)

Max Activating Token Index: 58

Text #12

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0133. Min Act: -0.0002

Data Index: 1384845 (Python Code)

Max Activating Token Index: 599

Text #13

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0131. Min Act: -0.0002

Data Index: 1595546 (Python Code)

Max Activating Token Index: 84

Text #14

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0131. Min Act: -0.0002

Data Index: 1645368 (Python Code)

Max Activating Token Index: 7

Text #15

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0131. Min Act: -0.0002

Data Index: 1591013 (Python Code)

Max Activating Token Index: 462

Text #16

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0131. Min Act: -0.0002

Data Index: 1499592 (Python Code)

Max Activating Token Index: 822

Text #17

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0131. Min Act: -0.0002

Data Index: 1644119 (Python Code)

Max Activating Token Index: 484

Text #18

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0130. Min Act: -0.0002

Data Index: 1581372 (Python Code)

Max Activating Token Index: 478

Text #19

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0130. Min Act: -0.0001

Data Index: 1620772 (Python Code)

Max Activating Token Index: 543