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

Dataset: The Pile

Neuron 2238 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0861. Min Range: -1.0861

Max Act: 1.0861. Min Act: -0.0000

Data Index: 469310 (The Pile)

Max Activating Token Index: 579

Text #1

Max Range: 1.0861. Min Range: -1.0861

Max Act: 0.9093. Min Act: -0.0000

Data Index: 1041036 (The Pile)

Max Activating Token Index: 1011

Text #2

Max Range: 1.0861. Min Range: -1.0861

Max Act: 0.9522. Min Act: -0.0000

Data Index: 1405501 (The Pile)

Max Activating Token Index: 660

Text #3

Max Range: 1.0861. Min Range: -1.0861

Max Act: 0.9222. Min Act: -0.0000

Data Index: 1900983 (The Pile)

Max Activating Token Index: 549

Text #4

Max Range: 1.0861. Min Range: -1.0861

Max Act: 0.9210. Min Act: -0.0000

Data Index: 1252797 (The Pile)

Max Activating Token Index: 1005

Text #5

Max Range: 1.0861. Min Range: -1.0861

Max Act: 0.7520. Min Act: -0.0000

Data Index: 271261 (The Pile)

Max Activating Token Index: 962

Text #6

Max Range: 1.0861. Min Range: -1.0861

Max Act: 1.0617. Min Act: -0.0000

Data Index: 1634198 (The Pile)

Max Activating Token Index: 866

Text #7

Max Range: 1.0861. Min Range: -1.0861

Max Act: 0.7831. Min Act: -0.0000

Data Index: 1057233 (The Pile)

Max Activating Token Index: 122

Text #8

Max Range: 1.0861. Min Range: -1.0861

Max Act: 0.8581. Min Act: -0.0000

Data Index: 1403181 (The Pile)

Max Activating Token Index: 130

Text #9

Max Range: 1.0861. Min Range: -1.0861

Max Act: 0.7965. Min Act: -0.0000

Data Index: 1287668 (The Pile)

Max Activating Token Index: 19

Text #10

Max Range: 1.0861. Min Range: -1.0861

Max Act: 0.7773. Min Act: -0.0000

Data Index: 1323424 (The Pile)

Max Activating Token Index: 236

Text #11

Max Range: 1.0861. Min Range: -1.0861

Max Act: 0.7302. Min Act: -0.0000

Data Index: 1005519 (The Pile)

Max Activating Token Index: 91

Text #12

Max Range: 1.0861. Min Range: -1.0861

Max Act: 0.8056. Min Act: -0.0000

Data Index: 1137845 (The Pile)

Max Activating Token Index: 46

Text #13

Max Range: 1.0861. Min Range: -1.0861

Max Act: 0.7281. Min Act: -0.0000

Data Index: 1415226 (The Pile)

Max Activating Token Index: 106

Text #14

Max Range: 1.0861. Min Range: -1.0861

Max Act: 0.7250. Min Act: -0.0000

Data Index: 1222645 (The Pile)

Max Activating Token Index: 127

Text #15

Max Range: 1.0861. Min Range: -1.0861

Max Act: 0.7568. Min Act: -0.0000

Data Index: 513617 (The Pile)

Max Activating Token Index: 72

Text #16

Max Range: 1.0861. Min Range: -1.0861

Max Act: 0.7322. Min Act: -0.0000

Data Index: 299485 (The Pile)

Max Activating Token Index: 455

Text #17

Max Range: 1.0861. Min Range: -1.0861

Max Act: 0.7183. Min Act: -0.0000

Data Index: 404349 (The Pile)

Max Activating Token Index: 744

Text #18

Max Range: 1.0861. Min Range: -1.0861

Max Act: 0.7476. Min Act: -0.0000

Data Index: 747310 (The Pile)

Max Activating Token Index: 114

Text #19

Max Range: 1.0861. Min Range: -1.0861

Max Act: 0.7400. Min Act: -0.0000

Data Index: 971598 (The Pile)

Max Activating Token Index: 127