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

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

Neuron 3827 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: 1.3063. Min Range: -1.3063

Max Act: 1.2330. Min Act: 0.0000

Data Index: 1430514 (Python Code)

Max Activating Token Index: 154

Text #1

Max Range: 1.3063. Min Range: -1.3063

Max Act: 1.3063. Min Act: -0.0000

Data Index: 1640549 (Python Code)

Max Activating Token Index: 443

Text #2

Max Range: 1.3063. Min Range: -1.3063

Max Act: 1.2814. Min Act: -0.0000

Data Index: 1379018 (Python Code)

Max Activating Token Index: 667

Text #3

Max Range: 1.3063. Min Range: -1.3063

Max Act: 1.1538. Min Act: -0.0000

Data Index: 759902 (C4 (Web Text))

Max Activating Token Index: 642

Text #4

Max Range: 1.3063. Min Range: -1.3063

Max Act: 1.1324. Min Act: 0.0000

Data Index: 1607162 (Python Code)

Max Activating Token Index: 38

Text #5

Max Range: 1.3063. Min Range: -1.3063

Max Act: 1.1216. Min Act: -0.0000

Data Index: 1383015 (Python Code)

Max Activating Token Index: 213

Text #6

Max Range: 1.3063. Min Range: -1.3063

Max Act: 1.1415. Min Act: -0.0000

Data Index: 951412 (C4 (Web Text))

Max Activating Token Index: 454

Text #7

Max Range: 1.3063. Min Range: -1.3063

Max Act: 1.0647. Min Act: -0.0000

Data Index: 807286 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 1.3063. Min Range: -1.3063

Max Act: 1.0076. Min Act: -0.0000

Data Index: 913964 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 1.3063. Min Range: -1.3063

Max Act: 1.0030. Min Act: -0.0000

Data Index: 780546 (C4 (Web Text))

Max Activating Token Index: 1008

Text #10

Max Range: 1.3063. Min Range: -1.3063

Max Act: 0.9863. Min Act: -0.0000

Data Index: 266467 (C4 (Web Text))

Max Activating Token Index: 794

Text #11

Max Range: 1.3063. Min Range: -1.3063

Max Act: 0.9279. Min Act: 0.0001

Data Index: 1542092 (Python Code)

Max Activating Token Index: 273

Text #12

Max Range: 1.3063. Min Range: -1.3063

Max Act: 0.9307. Min Act: -0.0000

Data Index: 854798 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 1.3063. Min Range: -1.3063

Max Act: 0.8982. Min Act: -0.0000

Data Index: 833675 (C4 (Web Text))

Max Activating Token Index: 471

Text #14

Max Range: 1.3063. Min Range: -1.3063

Max Act: 0.9004. Min Act: -0.0000

Data Index: 978363 (C4 (Web Text))

Max Activating Token Index: 557

Text #15

Max Range: 1.3063. Min Range: -1.3063

Max Act: 0.8387. Min Act: -0.0000

Data Index: 7156 (C4 (Web Text))

Max Activating Token Index: 389

Text #16

Max Range: 1.3063. Min Range: -1.3063

Max Act: 0.9341. Min Act: 0.0001

Data Index: 1415389 (Python Code)

Max Activating Token Index: 838

Text #17

Max Range: 1.3063. Min Range: -1.3063

Max Act: 0.9488. Min Act: -0.0000

Data Index: 1364812 (Python Code)

Max Activating Token Index: 905

Text #18

Max Range: 1.3063. Min Range: -1.3063

Max Act: 0.8869. Min Act: -0.0000

Data Index: 366530 (C4 (Web Text))

Max Activating Token Index: 257

Text #19

Max Range: 1.3063. Min Range: -1.3063

Max Act: 0.8746. Min Act: -0.0000

Data Index: 574464 (C4 (Web Text))

Max Activating Token Index: 19