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

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

Neuron 4570 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2567. Min Act: -0.0000

Data Index: 76531 (C4 (Web Text))

Max Activating Token Index: 194

Text #1

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2433. Min Act: -0.0000

Data Index: 33191 (C4 (Web Text))

Max Activating Token Index: 326

Text #2

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2136. Min Act: -0.0000

Data Index: 855728 (C4 (Web Text))

Max Activating Token Index: 256

Text #3

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2232. Min Act: -0.0000

Data Index: 289569 (C4 (Web Text))

Max Activating Token Index: 1019

Text #4

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2083. Min Act: -0.0000

Data Index: 445587 (C4 (Web Text))

Max Activating Token Index: 750

Text #5

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2122. Min Act: -0.0001

Data Index: 1123375 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2196. Min Act: -0.0000

Data Index: 698041 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2100. Min Act: -0.0000

Data Index: 1096635 (C4 (Web Text))

Max Activating Token Index: 307

Text #8

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2063. Min Act: -0.0000

Data Index: 370998 (C4 (Web Text))

Max Activating Token Index: 194

Text #9

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2202. Min Act: -0.0000

Data Index: 910981 (C4 (Web Text))

Max Activating Token Index: 581

Text #10

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1949. Min Act: -0.0001

Data Index: 685623 (C4 (Web Text))

Max Activating Token Index: 488

Text #11

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2014. Min Act: -0.0000

Data Index: 794579 (C4 (Web Text))

Max Activating Token Index: 297

Text #12

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1945. Min Act: -0.0000

Data Index: 99737 (C4 (Web Text))

Max Activating Token Index: 602

Text #13

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2081. Min Act: -0.0000

Data Index: 753994 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1899. Min Act: -0.0000

Data Index: 330 (C4 (Web Text))

Max Activating Token Index: 482

Text #15

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1903. Min Act: -0.0000

Data Index: 214566 (C4 (Web Text))

Max Activating Token Index: 449

Text #16

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1774. Min Act: -0.0000

Data Index: 767994 (C4 (Web Text))

Max Activating Token Index: 340

Text #17

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1721. Min Act: -0.0000

Data Index: 702624 (C4 (Web Text))

Max Activating Token Index: 192

Text #18

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1746. Min Act: -0.0000

Data Index: 1319519 (C4 (Web Text))

Max Activating Token Index: 619

Text #19

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1801. Min Act: -0.0000

Data Index: 311912 (C4 (Web Text))

Max Activating Token Index: 616