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

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

Neuron 3074 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0890. Min Range: -1.0890

Max Act: 1.0890. Min Act: -0.0000

Data Index: 373870 (C4 (Web Text))

Max Activating Token Index: 286

Text #1

Max Range: 1.0890. Min Range: -1.0890

Max Act: 1.0081. Min Act: -0.0001

Data Index: 1507813 (Python Code)

Max Activating Token Index: 864

Text #2

Max Range: 1.0890. Min Range: -1.0890

Max Act: 1.0845. Min Act: -0.0000

Data Index: 1216838 (C4 (Web Text))

Max Activating Token Index: 96

Text #3

Max Range: 1.0890. Min Range: -1.0890

Max Act: 1.0312. Min Act: -0.0001

Data Index: 1412005 (Python Code)

Max Activating Token Index: 379

Text #4

Max Range: 1.0890. Min Range: -1.0890

Max Act: 0.9599. Min Act: -0.0001

Data Index: 1953 (C4 (Web Text))

Max Activating Token Index: 687

Text #5

Max Range: 1.0890. Min Range: -1.0890

Max Act: 0.9691. Min Act: -0.0001

Data Index: 1576538 (Python Code)

Max Activating Token Index: 333

Text #6

Max Range: 1.0890. Min Range: -1.0890

Max Act: 0.8856. Min Act: -0.0001

Data Index: 1474480 (Python Code)

Max Activating Token Index: 289

Text #7

Max Range: 1.0890. Min Range: -1.0890

Max Act: 0.9587. Min Act: -0.0000

Data Index: 78780 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 1.0890. Min Range: -1.0890

Max Act: 1.0379. Min Act: -0.0000

Data Index: 716887 (C4 (Web Text))

Max Activating Token Index: 258

Text #9

Max Range: 1.0890. Min Range: -1.0890

Max Act: 0.9197. Min Act: -0.0000

Data Index: 19087 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 1.0890. Min Range: -1.0890

Max Act: 0.9132. Min Act: -0.0000

Data Index: 411900 (C4 (Web Text))

Max Activating Token Index: 606

Text #11

Max Range: 1.0890. Min Range: -1.0890

Max Act: 0.9114. Min Act: -0.0001

Data Index: 1392944 (Python Code)

Max Activating Token Index: 387

Text #12

Max Range: 1.0890. Min Range: -1.0890

Max Act: 0.9097. Min Act: -0.0000

Data Index: 431755 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 1.0890. Min Range: -1.0890

Max Act: 0.9054. Min Act: -0.0001

Data Index: 1348643 (C4 (Web Text))

Max Activating Token Index: 526

Text #14

Max Range: 1.0890. Min Range: -1.0890

Max Act: 0.8716. Min Act: -0.0001

Data Index: 1654188 (Python Code)

Max Activating Token Index: 14

Text #15

Max Range: 1.0890. Min Range: -1.0890

Max Act: 0.8518. Min Act: -0.0001

Data Index: 1433111 (Python Code)

Max Activating Token Index: 57

Text #16

Max Range: 1.0890. Min Range: -1.0890

Max Act: 0.8728. Min Act: -0.0001

Data Index: 1530764 (Python Code)

Max Activating Token Index: 51

Text #17

Max Range: 1.0890. Min Range: -1.0890

Max Act: 0.8675. Min Act: -0.0001

Data Index: 1645560 (Python Code)

Max Activating Token Index: 13

Text #18

Max Range: 1.0890. Min Range: -1.0890

Max Act: 0.8714. Min Act: -0.0000

Data Index: 313006 (C4 (Web Text))

Max Activating Token Index: 167

Text #19

Max Range: 1.0890. Min Range: -1.0890

Max Act: 0.9035. Min Act: -0.0000

Data Index: 1139386 (C4 (Web Text))

Max Activating Token Index: 521