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

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

Neuron 3832 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: 1.7886. Min Range: -1.7886

Max Act: 1.7886. Min Act: -0.0001

Data Index: 617133 (C4 (Web Text))

Max Activating Token Index: 221

Text #1

Max Range: 1.7886. Min Range: -1.7886

Max Act: 1.7592. Min Act: -0.0001

Data Index: 1067602 (C4 (Web Text))

Max Activating Token Index: 844

Text #2

Max Range: 1.7886. Min Range: -1.7886

Max Act: 1.6912. Min Act: -0.0001

Data Index: 194149 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 1.7886. Min Range: -1.7886

Max Act: 1.6283. Min Act: -0.0001

Data Index: 582181 (C4 (Web Text))

Max Activating Token Index: 802

Text #4

Max Range: 1.7886. Min Range: -1.7886

Max Act: 1.6863. Min Act: -0.0001

Data Index: 306574 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 1.7886. Min Range: -1.7886

Max Act: 1.5960. Min Act: -0.0001

Data Index: 549801 (C4 (Web Text))

Max Activating Token Index: 338

Text #6

Max Range: 1.7886. Min Range: -1.7886

Max Act: 1.5032. Min Act: -0.0001

Data Index: 1243862 (C4 (Web Text))

Max Activating Token Index: 983

Text #7

Max Range: 1.7886. Min Range: -1.7886

Max Act: 1.4953. Min Act: -0.0001

Data Index: 743977 (C4 (Web Text))

Max Activating Token Index: 462

Text #8

Max Range: 1.7886. Min Range: -1.7886

Max Act: 1.5718. Min Act: -0.0001

Data Index: 656780 (C4 (Web Text))

Max Activating Token Index: 342

Text #9

Max Range: 1.7886. Min Range: -1.7886

Max Act: 1.4344. Min Act: -0.0001

Data Index: 642890 (C4 (Web Text))

Max Activating Token Index: 829

Text #10

Max Range: 1.7886. Min Range: -1.7886

Max Act: 1.5191. Min Act: -0.0001

Data Index: 146430 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 1.7886. Min Range: -1.7886

Max Act: 1.4723. Min Act: -0.0001

Data Index: 974101 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 1.7886. Min Range: -1.7886

Max Act: 1.5140. Min Act: -0.0001

Data Index: 500203 (C4 (Web Text))

Max Activating Token Index: 159

Text #13

Max Range: 1.7886. Min Range: -1.7886

Max Act: 1.4452. Min Act: -0.0001

Data Index: 702019 (C4 (Web Text))

Max Activating Token Index: 584

Text #14

Max Range: 1.7886. Min Range: -1.7886

Max Act: 1.4435. Min Act: -0.0001

Data Index: 1026635 (C4 (Web Text))

Max Activating Token Index: 213

Text #15

Max Range: 1.7886. Min Range: -1.7886

Max Act: 1.5761. Min Act: -0.0001

Data Index: 887474 (C4 (Web Text))

Max Activating Token Index: 238

Text #16

Max Range: 1.7886. Min Range: -1.7886

Max Act: 1.5597. Min Act: -0.0001

Data Index: 378078 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 1.7886. Min Range: -1.7886

Max Act: 1.3600. Min Act: -0.0001

Data Index: 758522 (C4 (Web Text))

Max Activating Token Index: 970

Text #18

Max Range: 1.7886. Min Range: -1.7886

Max Act: 1.4758. Min Act: -0.0001

Data Index: 42598 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 1.7886. Min Range: -1.7886

Max Act: 1.3833. Min Act: -0.0001

Data Index: 1209099 (C4 (Web Text))

Max Activating Token Index: 461