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

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

Neuron 445 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: 1.4781. Min Range: -1.4781

Max Act: 1.4781. Min Act: -0.0000

Data Index: 374146 (C4 (Web Text))

Max Activating Token Index: 171

Text #1

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.3772. Min Act: -0.0000

Data Index: 1109777 (C4 (Web Text))

Max Activating Token Index: 945

Text #2

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.2499. Min Act: -0.0000

Data Index: 270303 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.3272. Min Act: -0.0000

Data Index: 409363 (C4 (Web Text))

Max Activating Token Index: 209

Text #4

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.3001. Min Act: -0.0000

Data Index: 1338400 (C4 (Web Text))

Max Activating Token Index: 421

Text #5

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.1935. Min Act: -0.0000

Data Index: 361418 (C4 (Web Text))

Max Activating Token Index: 849

Text #6

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.1967. Min Act: -0.0000

Data Index: 272090 (C4 (Web Text))

Max Activating Token Index: 396

Text #7

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.1950. Min Act: -0.0000

Data Index: 969885 (C4 (Web Text))

Max Activating Token Index: 550

Text #8

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.1914. Min Act: -0.0000

Data Index: 355376 (C4 (Web Text))

Max Activating Token Index: 438

Text #9

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.0944. Min Act: -0.0000

Data Index: 1080375 (C4 (Web Text))

Max Activating Token Index: 873

Text #10

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.1389. Min Act: -0.0000

Data Index: 772966 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.0869. Min Act: -0.0000

Data Index: 863970 (C4 (Web Text))

Max Activating Token Index: 264

Text #12

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.1839. Min Act: -0.0000

Data Index: 433963 (C4 (Web Text))

Max Activating Token Index: 478

Text #13

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.1157. Min Act: -0.0000

Data Index: 771071 (C4 (Web Text))

Max Activating Token Index: 543

Text #14

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.1545. Min Act: -0.0000

Data Index: 142848 (C4 (Web Text))

Max Activating Token Index: 739

Text #15

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.1755. Min Act: -0.0000

Data Index: 888293 (C4 (Web Text))

Max Activating Token Index: 1015

Text #16

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.1689. Min Act: -0.0000

Data Index: 601457 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.1028. Min Act: -0.0000

Data Index: 514199 (C4 (Web Text))

Max Activating Token Index: 210

Text #18

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.0338. Min Act: -0.0000

Data Index: 1084721 (C4 (Web Text))

Max Activating Token Index: 960

Text #19

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.0284. Min Act: -0.0000

Data Index: 210282 (C4 (Web Text))

Max Activating Token Index: 735