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

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

Neuron 4559 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.5887. Min Act: -0.0000

Data Index: 64965 (C4 (Web Text))

Max Activating Token Index: 321

Text #1

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.5020. Min Act: -0.0000

Data Index: 478941 (C4 (Web Text))

Max Activating Token Index: 913

Text #2

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.4628. Min Act: -0.0000

Data Index: 618833 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.4513. Min Act: -0.0000

Data Index: 1083107 (C4 (Web Text))

Max Activating Token Index: 308

Text #4

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.4174. Min Act: -0.0000

Data Index: 598254 (C4 (Web Text))

Max Activating Token Index: 590

Text #5

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.4303. Min Act: -0.0000

Data Index: 1188873 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.3982. Min Act: -0.0000

Data Index: 808818 (C4 (Web Text))

Max Activating Token Index: 853

Text #7

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.4295. Min Act: -0.0000

Data Index: 1257854 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.3927. Min Act: -0.0000

Data Index: 1087908 (C4 (Web Text))

Max Activating Token Index: 505

Text #9

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.3851. Min Act: 0.0000

Data Index: 1075085 (C4 (Web Text))

Max Activating Token Index: 123

Text #10

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.3968. Min Act: 0.0000

Data Index: 865721 (C4 (Web Text))

Max Activating Token Index: 786

Text #11

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.3910. Min Act: -0.0000

Data Index: 974744 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.3752. Min Act: -0.0000

Data Index: 1310229 (C4 (Web Text))

Max Activating Token Index: 1008

Text #13

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.4021. Min Act: -0.0000

Data Index: 210317 (C4 (Web Text))

Max Activating Token Index: 760

Text #14

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.3710. Min Act: -0.0000

Data Index: 776640 (C4 (Web Text))

Max Activating Token Index: 485

Text #15

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.3828. Min Act: -0.0000

Data Index: 1055835 (C4 (Web Text))

Max Activating Token Index: 707

Text #16

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.3715. Min Act: 0.0000

Data Index: 989896 (C4 (Web Text))

Max Activating Token Index: 194

Text #17

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.3784. Min Act: -0.0000

Data Index: 870881 (C4 (Web Text))

Max Activating Token Index: 623

Text #18

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.3697. Min Act: -0.0000

Data Index: 1123471 (C4 (Web Text))

Max Activating Token Index: 538

Text #19

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.3630. Min Act: -0.0000

Data Index: 450206 (C4 (Web Text))

Max Activating Token Index: 275