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

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

Neuron 3724 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.2439. Min Act: -0.0000

Data Index: 1291736 (C4 (Web Text))

Max Activating Token Index: 449

Text #1

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.2578. Min Act: -0.0000

Data Index: 1029537 (C4 (Web Text))

Max Activating Token Index: 97

Text #2

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.2342. Min Act: 0.0000

Data Index: 564806 (C4 (Web Text))

Max Activating Token Index: 93

Text #3

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.2184. Min Act: -0.0000

Data Index: 264275 (C4 (Web Text))

Max Activating Token Index: 194

Text #4

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.2078. Min Act: 0.0001

Data Index: 808052 (C4 (Web Text))

Max Activating Token Index: 307

Text #5

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.1864. Min Act: -0.0000

Data Index: 1001929 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.2080. Min Act: -0.0000

Data Index: 659873 (C4 (Web Text))

Max Activating Token Index: 261

Text #7

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.2015. Min Act: 0.0001

Data Index: 232487 (C4 (Web Text))

Max Activating Token Index: 793

Text #8

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.2081. Min Act: -0.0000

Data Index: 412067 (C4 (Web Text))

Max Activating Token Index: 367

Text #9

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.1986. Min Act: -0.0000

Data Index: 556165 (C4 (Web Text))

Max Activating Token Index: 794

Text #10

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.1997. Min Act: 0.0000

Data Index: 647354 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.1874. Min Act: -0.0000

Data Index: 343056 (C4 (Web Text))

Max Activating Token Index: 995

Text #12

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.1974. Min Act: -0.0000

Data Index: 1151345 (C4 (Web Text))

Max Activating Token Index: 784

Text #13

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.1920. Min Act: -0.0000

Data Index: 1239155 (C4 (Web Text))

Max Activating Token Index: 611

Text #14

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.1882. Min Act: -0.0000

Data Index: 1222595 (C4 (Web Text))

Max Activating Token Index: 385

Text #15

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.1886. Min Act: -0.0000

Data Index: 563584 (C4 (Web Text))

Max Activating Token Index: 234

Text #16

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.1908. Min Act: -0.0000

Data Index: 1012878 (C4 (Web Text))

Max Activating Token Index: 614

Text #17

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.1843. Min Act: 0.0001

Data Index: 369488 (C4 (Web Text))

Max Activating Token Index: 704

Text #18

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.1887. Min Act: -0.0000

Data Index: 537806 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.1836. Min Act: -0.0000

Data Index: 62372 (C4 (Web Text))

Max Activating Token Index: 193