Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1676 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.9695. Min Act: -0.0000

Data Index: 25095 (The Pile)

Max Activating Token Index: 913

Text #1

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.9783. Min Act: -0.0000

Data Index: 510273 (The Pile)

Max Activating Token Index: 729

Text #2

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.9065. Min Act: -0.0000

Data Index: 1527064 (The Pile)

Max Activating Token Index: 948

Text #3

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.9891. Min Act: -0.0000

Data Index: 1425269 (The Pile)

Max Activating Token Index: 742

Text #4

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.8955. Min Act: -0.0000

Data Index: 1967227 (The Pile)

Max Activating Token Index: 237

Text #5

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.8961. Min Act: -0.0000

Data Index: 1573025 (The Pile)

Max Activating Token Index: 814

Text #6

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.8194. Min Act: -0.0000

Data Index: 1805899 (The Pile)

Max Activating Token Index: 865

Text #7

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.8784. Min Act: -0.0000

Data Index: 1982615 (The Pile)

Max Activating Token Index: 255

Text #8

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.8451. Min Act: -0.0000

Data Index: 1971056 (The Pile)

Max Activating Token Index: 912

Text #9

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.9276. Min Act: -0.0000

Data Index: 937108 (The Pile)

Max Activating Token Index: 204

Text #10

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.8875. Min Act: -0.0000

Data Index: 1748644 (The Pile)

Max Activating Token Index: 785

Text #11

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.8367. Min Act: -0.0000

Data Index: 633264 (The Pile)

Max Activating Token Index: 837

Text #12

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.8681. Min Act: -0.0000

Data Index: 250111 (The Pile)

Max Activating Token Index: 348

Text #13

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.9504. Min Act: -0.0000

Data Index: 430851 (The Pile)

Max Activating Token Index: 164

Text #14

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.8868. Min Act: -0.0000

Data Index: 1536878 (The Pile)

Max Activating Token Index: 619

Text #15

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.7113. Min Act: -0.0000

Data Index: 690255 (The Pile)

Max Activating Token Index: 752

Text #16

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.7791. Min Act: -0.0000

Data Index: 661689 (The Pile)

Max Activating Token Index: 80

Text #17

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.9207. Min Act: -0.0000

Data Index: 1034646 (The Pile)

Max Activating Token Index: 682

Text #18

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.8538. Min Act: -0.0000

Data Index: 1375723 (The Pile)

Max Activating Token Index: 185

Text #19

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.9096. Min Act: -0.0000

Data Index: 731599 (The Pile)

Max Activating Token Index: 939