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

Dataset: The Pile

Neuron 4870 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: 1.4340. Min Range: -1.4340

Max Act: 1.4340. Min Act: -0.0000

Data Index: 449981 (The Pile)

Max Activating Token Index: 295

Text #1

Max Range: 1.4340. Min Range: -1.4340

Max Act: 1.1302. Min Act: -0.0000

Data Index: 1486646 (The Pile)

Max Activating Token Index: 644

Text #2

Max Range: 1.4340. Min Range: -1.4340

Max Act: 1.1194. Min Act: -0.0000

Data Index: 882684 (The Pile)

Max Activating Token Index: 208

Text #3

Max Range: 1.4340. Min Range: -1.4340

Max Act: 1.0727. Min Act: -0.0000

Data Index: 1980458 (The Pile)

Max Activating Token Index: 180

Text #4

Max Range: 1.4340. Min Range: -1.4340

Max Act: 1.0721. Min Act: -0.0000

Data Index: 497171 (The Pile)

Max Activating Token Index: 640

Text #5

Max Range: 1.4340. Min Range: -1.4340

Max Act: 0.8816. Min Act: -0.0000

Data Index: 1927086 (The Pile)

Max Activating Token Index: 815

Text #6

Max Range: 1.4340. Min Range: -1.4340

Max Act: 0.9506. Min Act: -0.0000

Data Index: 1673242 (The Pile)

Max Activating Token Index: 623

Text #7

Max Range: 1.4340. Min Range: -1.4340

Max Act: 0.9748. Min Act: -0.0000

Data Index: 1136494 (The Pile)

Max Activating Token Index: 313

Text #8

Max Range: 1.4340. Min Range: -1.4340

Max Act: 0.9664. Min Act: -0.0000

Data Index: 17208 (The Pile)

Max Activating Token Index: 512

Text #9

Max Range: 1.4340. Min Range: -1.4340

Max Act: 0.9120. Min Act: -0.0000

Data Index: 1981808 (The Pile)

Max Activating Token Index: 818

Text #10

Max Range: 1.4340. Min Range: -1.4340

Max Act: 0.9512. Min Act: -0.0000

Data Index: 1248575 (The Pile)

Max Activating Token Index: 948

Text #11

Max Range: 1.4340. Min Range: -1.4340

Max Act: 0.9785. Min Act: -0.0000

Data Index: 605299 (The Pile)

Max Activating Token Index: 755

Text #12

Max Range: 1.4340. Min Range: -1.4340

Max Act: 0.9239. Min Act: -0.0000

Data Index: 1451456 (The Pile)

Max Activating Token Index: 675

Text #13

Max Range: 1.4340. Min Range: -1.4340

Max Act: 0.9117. Min Act: -0.0000

Data Index: 74870 (The Pile)

Max Activating Token Index: 76

Text #14

Max Range: 1.4340. Min Range: -1.4340

Max Act: 0.8500. Min Act: -0.0000

Data Index: 945180 (The Pile)

Max Activating Token Index: 726

Text #15

Max Range: 1.4340. Min Range: -1.4340

Max Act: 0.8628. Min Act: -0.0000

Data Index: 1417835 (The Pile)

Max Activating Token Index: 542

Text #16

Max Range: 1.4340. Min Range: -1.4340

Max Act: 0.8804. Min Act: -0.0000

Data Index: 560362 (The Pile)

Max Activating Token Index: 98

Text #17

Max Range: 1.4340. Min Range: -1.4340

Max Act: 0.8217. Min Act: -0.0000

Data Index: 1395677 (The Pile)

Max Activating Token Index: 1019

Text #18

Max Range: 1.4340. Min Range: -1.4340

Max Act: 0.7594. Min Act: -0.0000

Data Index: 1338972 (The Pile)

Max Activating Token Index: 794

Text #19

Max Range: 1.4340. Min Range: -1.4340

Max Act: 0.7745. Min Act: -0.0000

Data Index: 1961581 (The Pile)

Max Activating Token Index: 641