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

Dataset: The Pile

Neuron 4968 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: 1.0522. Min Range: -1.0522

Max Act: 0.9778. Min Act: -0.0000

Data Index: 994102 (The Pile)

Max Activating Token Index: 865

Text #1

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.9527. Min Act: -0.0000

Data Index: 1804872 (The Pile)

Max Activating Token Index: 246

Text #2

Max Range: 1.0522. Min Range: -1.0522

Max Act: 1.0522. Min Act: -0.0000

Data Index: 984973 (The Pile)

Max Activating Token Index: 63

Text #3

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.8727. Min Act: -0.0000

Data Index: 91918 (The Pile)

Max Activating Token Index: 440

Text #4

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.8888. Min Act: -0.0000

Data Index: 1451963 (The Pile)

Max Activating Token Index: 354

Text #5

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.9481. Min Act: -0.0000

Data Index: 1365306 (The Pile)

Max Activating Token Index: 425

Text #6

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.9698. Min Act: -0.0000

Data Index: 856944 (The Pile)

Max Activating Token Index: 259

Text #7

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.9204. Min Act: -0.0000

Data Index: 1773769 (The Pile)

Max Activating Token Index: 538

Text #8

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.8385. Min Act: -0.0000

Data Index: 894961 (The Pile)

Max Activating Token Index: 241

Text #9

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.8122. Min Act: -0.0000

Data Index: 692585 (The Pile)

Max Activating Token Index: 433

Text #10

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.8225. Min Act: -0.0000

Data Index: 1064247 (The Pile)

Max Activating Token Index: 856

Text #11

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.9408. Min Act: -0.0000

Data Index: 466006 (The Pile)

Max Activating Token Index: 948

Text #12

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.7975. Min Act: -0.0000

Data Index: 1323827 (The Pile)

Max Activating Token Index: 79

Text #13

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.9297. Min Act: -0.0000

Data Index: 1460971 (The Pile)

Max Activating Token Index: 310

Text #14

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.8351. Min Act: -0.0000

Data Index: 1143161 (The Pile)

Max Activating Token Index: 821

Text #15

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.8238. Min Act: -0.0001

Data Index: 190591 (The Pile)

Max Activating Token Index: 412

Text #16

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.7430. Min Act: -0.0000

Data Index: 1576254 (The Pile)

Max Activating Token Index: 331

Text #17

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.8308. Min Act: -0.0000

Data Index: 470101 (The Pile)

Max Activating Token Index: 1003

Text #18

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.7916. Min Act: -0.0000

Data Index: 1415688 (The Pile)

Max Activating Token Index: 600

Text #19

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.8289. Min Act: -0.0000

Data Index: 173025 (The Pile)

Max Activating Token Index: 199