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

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

Neuron 2973 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.7141. Min Act: -0.0000

Data Index: 1389025 (Python Code)

Max Activating Token Index: 603

Text #1

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.6887. Min Act: -0.0000

Data Index: 1611599 (Python Code)

Max Activating Token Index: 823

Text #2

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.6378. Min Act: -0.0000

Data Index: 1448480 (Python Code)

Max Activating Token Index: 672

Text #3

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.6127. Min Act: -0.0000

Data Index: 1373998 (Python Code)

Max Activating Token Index: 227

Text #4

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.5941. Min Act: -0.0000

Data Index: 1611866 (Python Code)

Max Activating Token Index: 290

Text #5

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.5550. Min Act: -0.0000

Data Index: 1375705 (Python Code)

Max Activating Token Index: 1002

Text #6

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.5139. Min Act: -0.0000

Data Index: 1441047 (Python Code)

Max Activating Token Index: 792

Text #7

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.5126. Min Act: -0.0000

Data Index: 1585404 (Python Code)

Max Activating Token Index: 246

Text #8

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.4823. Min Act: -0.0000

Data Index: 1484167 (Python Code)

Max Activating Token Index: 834

Text #9

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.4964. Min Act: -0.0000

Data Index: 1418811 (Python Code)

Max Activating Token Index: 136

Text #10

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.4864. Min Act: -0.0000

Data Index: 1619223 (Python Code)

Max Activating Token Index: 314

Text #11

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.4782. Min Act: -0.0000

Data Index: 1590563 (Python Code)

Max Activating Token Index: 147

Text #12

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.4416. Min Act: -0.0000

Data Index: 625755 (C4 (Web Text))

Max Activating Token Index: 544

Text #13

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.4395. Min Act: -0.0000

Data Index: 1489243 (Python Code)

Max Activating Token Index: 607

Text #14

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.4044. Min Act: -0.0000

Data Index: 335093 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.3594. Min Act: -0.0000

Data Index: 957569 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.3568. Min Act: -0.0000

Data Index: 1574830 (Python Code)

Max Activating Token Index: 940

Text #17

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.3785. Min Act: -0.0000

Data Index: 923801 (C4 (Web Text))

Max Activating Token Index: 563

Text #18

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.3845. Min Act: -0.0000

Data Index: 1410903 (Python Code)

Max Activating Token Index: 280

Text #19

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.3733. Min Act: -0.0000

Data Index: 1312225 (C4 (Web Text))

Max Activating Token Index: 983