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

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

Neuron 878 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5094. Min Range: -1.5094

Max Act: 1.5094. Min Act: -0.0001

Data Index: 321490 (C4 (Web Text))

Max Activating Token Index: 778

Text #1

Max Range: 1.5094. Min Range: -1.5094

Max Act: 1.2081. Min Act: -0.0001

Data Index: 397258 (C4 (Web Text))

Max Activating Token Index: 964

Text #2

Max Range: 1.5094. Min Range: -1.5094

Max Act: 1.2835. Min Act: -0.0001

Data Index: 544772 (C4 (Web Text))

Max Activating Token Index: 783

Text #3

Max Range: 1.5094. Min Range: -1.5094

Max Act: 1.0127. Min Act: -0.0001

Data Index: 800133 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 1.5094. Min Range: -1.5094

Max Act: 1.1307. Min Act: -0.0001

Data Index: 13169 (C4 (Web Text))

Max Activating Token Index: 416

Text #5

Max Range: 1.5094. Min Range: -1.5094

Max Act: 0.9445. Min Act: -0.0001

Data Index: 880670 (C4 (Web Text))

Max Activating Token Index: 284

Text #6

Max Range: 1.5094. Min Range: -1.5094

Max Act: 1.0438. Min Act: -0.0001

Data Index: 1196327 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 1.5094. Min Range: -1.5094

Max Act: 0.9922. Min Act: -0.0001

Data Index: 917666 (C4 (Web Text))

Max Activating Token Index: 658

Text #8

Max Range: 1.5094. Min Range: -1.5094

Max Act: 1.0115. Min Act: -0.0001

Data Index: 1123207 (C4 (Web Text))

Max Activating Token Index: 865

Text #9

Max Range: 1.5094. Min Range: -1.5094

Max Act: 0.9987. Min Act: -0.0001

Data Index: 543835 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 1.5094. Min Range: -1.5094

Max Act: 0.9199. Min Act: -0.0001

Data Index: 215031 (C4 (Web Text))

Max Activating Token Index: 786

Text #11

Max Range: 1.5094. Min Range: -1.5094

Max Act: 0.9937. Min Act: -0.0001

Data Index: 834005 (C4 (Web Text))

Max Activating Token Index: 866

Text #12

Max Range: 1.5094. Min Range: -1.5094

Max Act: 0.8880. Min Act: -0.0001

Data Index: 611234 (C4 (Web Text))

Max Activating Token Index: 96

Text #13

Max Range: 1.5094. Min Range: -1.5094

Max Act: 0.9371. Min Act: -0.0001

Data Index: 895720 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 1.5094. Min Range: -1.5094

Max Act: 0.9449. Min Act: -0.0001

Data Index: 233147 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 1.5094. Min Range: -1.5094

Max Act: 0.8333. Min Act: -0.0001

Data Index: 1054015 (C4 (Web Text))

Max Activating Token Index: 219

Text #16

Max Range: 1.5094. Min Range: -1.5094

Max Act: 0.9275. Min Act: -0.0001

Data Index: 1272168 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 1.5094. Min Range: -1.5094

Max Act: 0.9322. Min Act: -0.0001

Data Index: 528073 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 1.5094. Min Range: -1.5094

Max Act: 0.8824. Min Act: -0.0001

Data Index: 674911 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 1.5094. Min Range: -1.5094

Max Act: 0.8400. Min Act: -0.0001

Data Index: 859387 (C4 (Web Text))

Max Activating Token Index: 508