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

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

Neuron 3874 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0113. Min Range: -1.0113

Max Act: 0.9175. Min Act: -0.0000

Data Index: 1086055 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 1.0113. Min Range: -1.0113

Max Act: 1.0113. Min Act: -0.0000

Data Index: 746854 (C4 (Web Text))

Max Activating Token Index: 431

Text #2

Max Range: 1.0113. Min Range: -1.0113

Max Act: 0.8833. Min Act: -0.0000

Data Index: 880221 (C4 (Web Text))

Max Activating Token Index: 454

Text #3

Max Range: 1.0113. Min Range: -1.0113

Max Act: 0.7554. Min Act: -0.0000

Data Index: 750732 (C4 (Web Text))

Max Activating Token Index: 122

Text #4

Max Range: 1.0113. Min Range: -1.0113

Max Act: 0.6969. Min Act: -0.0000

Data Index: 347385 (C4 (Web Text))

Max Activating Token Index: 615

Text #5

Max Range: 1.0113. Min Range: -1.0113

Max Act: 0.7539. Min Act: -0.0000

Data Index: 1341008 (C4 (Web Text))

Max Activating Token Index: 898

Text #6

Max Range: 1.0113. Min Range: -1.0113

Max Act: 0.6943. Min Act: -0.0000

Data Index: 731962 (C4 (Web Text))

Max Activating Token Index: 724

Text #7

Max Range: 1.0113. Min Range: -1.0113

Max Act: 0.6592. Min Act: -0.0000

Data Index: 717247 (C4 (Web Text))

Max Activating Token Index: 941

Text #8

Max Range: 1.0113. Min Range: -1.0113

Max Act: 0.6192. Min Act: -0.0000

Data Index: 1303459 (C4 (Web Text))

Max Activating Token Index: 185

Text #9

Max Range: 1.0113. Min Range: -1.0113

Max Act: 0.6252. Min Act: -0.0000

Data Index: 485451 (C4 (Web Text))

Max Activating Token Index: 558

Text #10

Max Range: 1.0113. Min Range: -1.0113

Max Act: 0.5812. Min Act: -0.0000

Data Index: 1214979 (C4 (Web Text))

Max Activating Token Index: 202

Text #11

Max Range: 1.0113. Min Range: -1.0113

Max Act: 0.5972. Min Act: -0.0000

Data Index: 334460 (C4 (Web Text))

Max Activating Token Index: 871

Text #12

Max Range: 1.0113. Min Range: -1.0113

Max Act: 0.5455. Min Act: -0.0000

Data Index: 645403 (C4 (Web Text))

Max Activating Token Index: 248

Text #13

Max Range: 1.0113. Min Range: -1.0113

Max Act: 0.5354. Min Act: -0.0000

Data Index: 726194 (C4 (Web Text))

Max Activating Token Index: 821

Text #14

Max Range: 1.0113. Min Range: -1.0113

Max Act: 0.5834. Min Act: -0.0000

Data Index: 1080744 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 1.0113. Min Range: -1.0113

Max Act: 0.5547. Min Act: 0.0000

Data Index: 868571 (C4 (Web Text))

Max Activating Token Index: 777

Text #16

Max Range: 1.0113. Min Range: -1.0113

Max Act: 0.5393. Min Act: -0.0000

Data Index: 374343 (C4 (Web Text))

Max Activating Token Index: 743

Text #17

Max Range: 1.0113. Min Range: -1.0113

Max Act: 0.4771. Min Act: -0.0000

Data Index: 1213186 (C4 (Web Text))

Max Activating Token Index: 1013

Text #18

Max Range: 1.0113. Min Range: -1.0113

Max Act: 0.5001. Min Act: -0.0000

Data Index: 1090779 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 1.0113. Min Range: -1.0113

Max Act: 0.5426. Min Act: -0.0000

Data Index: 1134926 (C4 (Web Text))

Max Activating Token Index: 974