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

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

Neuron 3345 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2004. Min Range: -1.2004

Max Act: 1.2004. Min Act: -0.0000

Data Index: 144649 (C4 (Web Text))

Max Activating Token Index: 771

Text #1

Max Range: 1.2004. Min Range: -1.2004

Max Act: 0.9853. Min Act: -0.0000

Data Index: 214764 (C4 (Web Text))

Max Activating Token Index: 636

Text #2

Max Range: 1.2004. Min Range: -1.2004

Max Act: 0.9747. Min Act: -0.0000

Data Index: 1234238 (C4 (Web Text))

Max Activating Token Index: 753

Text #3

Max Range: 1.2004. Min Range: -1.2004

Max Act: 0.7936. Min Act: -0.0000

Data Index: 292964 (C4 (Web Text))

Max Activating Token Index: 1022

Text #4

Max Range: 1.2004. Min Range: -1.2004

Max Act: 0.7867. Min Act: -0.0000

Data Index: 361137 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 1.2004. Min Range: -1.2004

Max Act: 0.8122. Min Act: -0.0000

Data Index: 62951 (C4 (Web Text))

Max Activating Token Index: 531

Text #6

Max Range: 1.2004. Min Range: -1.2004

Max Act: 0.7189. Min Act: -0.0000

Data Index: 823316 (C4 (Web Text))

Max Activating Token Index: 642

Text #7

Max Range: 1.2004. Min Range: -1.2004

Max Act: 0.7432. Min Act: -0.0000

Data Index: 952991 (C4 (Web Text))

Max Activating Token Index: 388

Text #8

Max Range: 1.2004. Min Range: -1.2004

Max Act: 0.7320. Min Act: -0.0000

Data Index: 1113691 (C4 (Web Text))

Max Activating Token Index: 116

Text #9

Max Range: 1.2004. Min Range: -1.2004

Max Act: 0.7253. Min Act: -0.0000

Data Index: 1350068 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 1.2004. Min Range: -1.2004

Max Act: 0.7099. Min Act: -0.0000

Data Index: 362383 (C4 (Web Text))

Max Activating Token Index: 465

Text #11

Max Range: 1.2004. Min Range: -1.2004

Max Act: 0.6996. Min Act: -0.0000

Data Index: 1028620 (C4 (Web Text))

Max Activating Token Index: 703

Text #12

Max Range: 1.2004. Min Range: -1.2004

Max Act: 0.7288. Min Act: -0.0000

Data Index: 1086931 (C4 (Web Text))

Max Activating Token Index: 554

Text #13

Max Range: 1.2004. Min Range: -1.2004

Max Act: 0.6956. Min Act: -0.0000

Data Index: 1108985 (C4 (Web Text))

Max Activating Token Index: 807

Text #14

Max Range: 1.2004. Min Range: -1.2004

Max Act: 0.6763. Min Act: -0.0000

Data Index: 1106366 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 1.2004. Min Range: -1.2004

Max Act: 0.6849. Min Act: -0.0000

Data Index: 560900 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 1.2004. Min Range: -1.2004

Max Act: 0.6072. Min Act: -0.0000

Data Index: 134629 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 1.2004. Min Range: -1.2004

Max Act: 0.6319. Min Act: -0.0000

Data Index: 1250276 (C4 (Web Text))

Max Activating Token Index: 593

Text #18

Max Range: 1.2004. Min Range: -1.2004

Max Act: 0.6257. Min Act: -0.0000

Data Index: 1175613 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 1.2004. Min Range: -1.2004

Max Act: 0.5442. Min Act: -0.0000

Data Index: 703181 (C4 (Web Text))

Max Activating Token Index: 84