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

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

Neuron 1673 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3871. Min Range: -2.3871

Max Act: 2.2299. Min Act: -0.0000

Data Index: 832159 (C4 (Web Text))

Max Activating Token Index: 512

Text #1

Max Range: 2.3871. Min Range: -2.3871

Max Act: 2.3871. Min Act: -0.0000

Data Index: 626569 (C4 (Web Text))

Max Activating Token Index: 558

Text #2

Max Range: 2.3871. Min Range: -2.3871

Max Act: 2.3355. Min Act: -0.0000

Data Index: 88240 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 2.3871. Min Range: -2.3871

Max Act: 2.1850. Min Act: -0.0000

Data Index: 973528 (C4 (Web Text))

Max Activating Token Index: 975

Text #4

Max Range: 2.3871. Min Range: -2.3871

Max Act: 2.2724. Min Act: -0.0000

Data Index: 34145 (C4 (Web Text))

Max Activating Token Index: 617

Text #5

Max Range: 2.3871. Min Range: -2.3871

Max Act: 2.1359. Min Act: -0.0000

Data Index: 472691 (C4 (Web Text))

Max Activating Token Index: 479

Text #6

Max Range: 2.3871. Min Range: -2.3871

Max Act: 1.9933. Min Act: -0.0000

Data Index: 407835 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 2.3871. Min Range: -2.3871

Max Act: 2.1083. Min Act: -0.0000

Data Index: 975669 (C4 (Web Text))

Max Activating Token Index: 40

Text #8

Max Range: 2.3871. Min Range: -2.3871

Max Act: 2.0570. Min Act: -0.0000

Data Index: 627775 (C4 (Web Text))

Max Activating Token Index: 840

Text #9

Max Range: 2.3871. Min Range: -2.3871

Max Act: 2.0300. Min Act: -0.0000

Data Index: 504154 (C4 (Web Text))

Max Activating Token Index: 697

Text #10

Max Range: 2.3871. Min Range: -2.3871

Max Act: 1.9996. Min Act: -0.0000

Data Index: 730215 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 2.3871. Min Range: -2.3871

Max Act: 1.9759. Min Act: -0.0000

Data Index: 318441 (C4 (Web Text))

Max Activating Token Index: 669

Text #12

Max Range: 2.3871. Min Range: -2.3871

Max Act: 1.8211. Min Act: -0.0000

Data Index: 1645982 (Python Code)

Max Activating Token Index: 150

Text #13

Max Range: 2.3871. Min Range: -2.3871

Max Act: 2.0072. Min Act: -0.0000

Data Index: 972240 (C4 (Web Text))

Max Activating Token Index: 903

Text #14

Max Range: 2.3871. Min Range: -2.3871

Max Act: 1.8961. Min Act: -0.0000

Data Index: 187395 (C4 (Web Text))

Max Activating Token Index: 354

Text #15

Max Range: 2.3871. Min Range: -2.3871

Max Act: 1.7646. Min Act: -0.0000

Data Index: 395525 (C4 (Web Text))

Max Activating Token Index: 225

Text #16

Max Range: 2.3871. Min Range: -2.3871

Max Act: 1.8639. Min Act: -0.0000

Data Index: 1323843 (C4 (Web Text))

Max Activating Token Index: 919

Text #17

Max Range: 2.3871. Min Range: -2.3871

Max Act: 1.7565. Min Act: -0.0000

Data Index: 1513121 (Python Code)

Max Activating Token Index: 1016

Text #18

Max Range: 2.3871. Min Range: -2.3871

Max Act: 1.8581. Min Act: -0.0000

Data Index: 286586 (C4 (Web Text))

Max Activating Token Index: 759

Text #19

Max Range: 2.3871. Min Range: -2.3871

Max Act: 1.6307. Min Act: -0.0000

Data Index: 192372 (C4 (Web Text))

Max Activating Token Index: 755