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

Dataset: The Pile

Neuron 441 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9578. Min Range: -0.9578

Max Act: 0.9578. Min Act: -0.0000

Data Index: 776189 (The Pile)

Max Activating Token Index: 53

Text #1

Max Range: 0.9578. Min Range: -0.9578

Max Act: 0.8909. Min Act: -0.0000

Data Index: 1006185 (The Pile)

Max Activating Token Index: 752

Text #2

Max Range: 0.9578. Min Range: -0.9578

Max Act: 0.9115. Min Act: -0.0000

Data Index: 290451 (The Pile)

Max Activating Token Index: 404

Text #3

Max Range: 0.9578. Min Range: -0.9578

Max Act: 0.9248. Min Act: -0.0000

Data Index: 602516 (The Pile)

Max Activating Token Index: 180

Text #4

Max Range: 0.9578. Min Range: -0.9578

Max Act: 0.8450. Min Act: -0.0000

Data Index: 1364361 (The Pile)

Max Activating Token Index: 706

Text #5

Max Range: 0.9578. Min Range: -0.9578

Max Act: 0.8317. Min Act: -0.0000

Data Index: 395868 (The Pile)

Max Activating Token Index: 448

Text #6

Max Range: 0.9578. Min Range: -0.9578

Max Act: 0.8343. Min Act: -0.0000

Data Index: 191485 (The Pile)

Max Activating Token Index: 88

Text #7

Max Range: 0.9578. Min Range: -0.9578

Max Act: 0.7635. Min Act: -0.0000

Data Index: 586184 (The Pile)

Max Activating Token Index: 158

Text #8

Max Range: 0.9578. Min Range: -0.9578

Max Act: 0.7985. Min Act: -0.0000

Data Index: 177813 (The Pile)

Max Activating Token Index: 811

Text #9

Max Range: 0.9578. Min Range: -0.9578

Max Act: 0.7658. Min Act: -0.0000

Data Index: 1242952 (The Pile)

Max Activating Token Index: 511

Text #10

Max Range: 0.9578. Min Range: -0.9578

Max Act: 0.7839. Min Act: -0.0000

Data Index: 1726339 (The Pile)

Max Activating Token Index: 561

Text #11

Max Range: 0.9578. Min Range: -0.9578

Max Act: 0.7307. Min Act: -0.0000

Data Index: 196415 (The Pile)

Max Activating Token Index: 421

Text #12

Max Range: 0.9578. Min Range: -0.9578

Max Act: 0.7050. Min Act: -0.0000

Data Index: 73156 (The Pile)

Max Activating Token Index: 311

Text #13

Max Range: 0.9578. Min Range: -0.9578

Max Act: 0.7390. Min Act: -0.0000

Data Index: 714107 (The Pile)

Max Activating Token Index: 167

Text #14

Max Range: 0.9578. Min Range: -0.9578

Max Act: 0.7253. Min Act: -0.0000

Data Index: 517626 (The Pile)

Max Activating Token Index: 340

Text #15

Max Range: 0.9578. Min Range: -0.9578

Max Act: 0.7116. Min Act: -0.0000

Data Index: 1288523 (The Pile)

Max Activating Token Index: 799

Text #16

Max Range: 0.9578. Min Range: -0.9578

Max Act: 0.6138. Min Act: -0.0000

Data Index: 795091 (The Pile)

Max Activating Token Index: 227

Text #17

Max Range: 0.9578. Min Range: -0.9578

Max Act: 0.7028. Min Act: -0.0000

Data Index: 1875333 (The Pile)

Max Activating Token Index: 709

Text #18

Max Range: 0.9578. Min Range: -0.9578

Max Act: 0.6990. Min Act: -0.0000

Data Index: 282090 (The Pile)

Max Activating Token Index: 854

Text #19

Max Range: 0.9578. Min Range: -0.9578

Max Act: 0.7190. Min Act: -0.0000

Data Index: 1988365 (The Pile)

Max Activating Token Index: 132