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

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

Neuron 4571 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.7146. Min Act: -0.0000

Data Index: 1172294 (C4 (Web Text))

Max Activating Token Index: 950

Text #1

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.7918. Min Act: -0.0000

Data Index: 265862 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.7545. Min Act: -0.0000

Data Index: 1180038 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.5320. Min Act: -0.0000

Data Index: 1046985 (C4 (Web Text))

Max Activating Token Index: 500

Text #4

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.5086. Min Act: -0.0000

Data Index: 1061139 (C4 (Web Text))

Max Activating Token Index: 491

Text #5

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.3704. Min Act: -0.0000

Data Index: 944407 (C4 (Web Text))

Max Activating Token Index: 955

Text #6

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.4714. Min Act: -0.0000

Data Index: 1625787 (Python Code)

Max Activating Token Index: 845

Text #7

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.3724. Min Act: -0.0000

Data Index: 403736 (C4 (Web Text))

Max Activating Token Index: 1007

Text #8

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.1708. Min Act: -0.0000

Data Index: 1601707 (Python Code)

Max Activating Token Index: 847

Text #9

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.4697. Min Act: -0.0000

Data Index: 1333453 (C4 (Web Text))

Max Activating Token Index: 185

Text #10

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.2756. Min Act: -0.0000

Data Index: 1650114 (Python Code)

Max Activating Token Index: 633

Text #11

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.3957. Min Act: -0.0000

Data Index: 1364118 (Python Code)

Max Activating Token Index: 591

Text #12

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.2054. Min Act: -0.0000

Data Index: 1240083 (C4 (Web Text))

Max Activating Token Index: 246

Text #13

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.1242. Min Act: -0.0000

Data Index: 684004 (C4 (Web Text))

Max Activating Token Index: 283

Text #14

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.1295. Min Act: -0.0000

Data Index: 1406817 (Python Code)

Max Activating Token Index: 235

Text #15

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.2218. Min Act: -0.0000

Data Index: 1487077 (Python Code)

Max Activating Token Index: 693

Text #16

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.0584. Min Act: -0.0000

Data Index: 1432766 (Python Code)

Max Activating Token Index: 570

Text #17

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.0836. Min Act: -0.0000

Data Index: 1002998 (C4 (Web Text))

Max Activating Token Index: 697

Text #18

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.0636. Min Act: -0.0000

Data Index: 998290 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.0249. Min Act: -0.0000

Data Index: 1359095 (C4 (Web Text))

Max Activating Token Index: 125