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

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

Neuron 462 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: 1.4951. Min Range: -1.4951

Max Act: 1.3784. Min Act: -0.0000

Data Index: 409370 (C4 (Web Text))

Max Activating Token Index: 976

Text #1

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.4951. Min Act: -0.0000

Data Index: 1159392 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.3697. Min Act: -0.0000

Data Index: 712 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.4083. Min Act: -0.0000

Data Index: 84463 (C4 (Web Text))

Max Activating Token Index: 992

Text #4

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.3230. Min Act: -0.0000

Data Index: 1070522 (C4 (Web Text))

Max Activating Token Index: 659

Text #5

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.2691. Min Act: -0.0000

Data Index: 967359 (C4 (Web Text))

Max Activating Token Index: 795

Text #6

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.2242. Min Act: -0.0000

Data Index: 545122 (C4 (Web Text))

Max Activating Token Index: 840

Text #7

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.2742. Min Act: -0.0000

Data Index: 1192156 (C4 (Web Text))

Max Activating Token Index: 909

Text #8

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.3009. Min Act: -0.0000

Data Index: 312322 (C4 (Web Text))

Max Activating Token Index: 798

Text #9

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.3298. Min Act: -0.0000

Data Index: 1064782 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.2959. Min Act: -0.0000

Data Index: 1164631 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.2056. Min Act: -0.0000

Data Index: 155171 (C4 (Web Text))

Max Activating Token Index: 722

Text #12

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.2439. Min Act: -0.0000

Data Index: 601329 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.2918. Min Act: -0.0000

Data Index: 120510 (C4 (Web Text))

Max Activating Token Index: 908

Text #14

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.1961. Min Act: -0.0000

Data Index: 1493675 (Python Code)

Max Activating Token Index: 717

Text #15

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.2256. Min Act: -0.0000

Data Index: 495050 (C4 (Web Text))

Max Activating Token Index: 945

Text #16

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.2391. Min Act: -0.0000

Data Index: 1025051 (C4 (Web Text))

Max Activating Token Index: 76

Text #17

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.2602. Min Act: -0.0000

Data Index: 1252381 (C4 (Web Text))

Max Activating Token Index: 544

Text #18

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.1866. Min Act: -0.0000

Data Index: 544051 (C4 (Web Text))

Max Activating Token Index: 469

Text #19

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.2227. Min Act: -0.0000

Data Index: 294599 (C4 (Web Text))

Max Activating Token Index: 864