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

Dataset: The Pile

Neuron 3377 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.9522. Min Act: -0.0000

Data Index: 1059536 (The Pile)

Max Activating Token Index: 199

Text #1

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.8795. Min Act: -0.0000

Data Index: 827291 (The Pile)

Max Activating Token Index: 918

Text #2

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.8298. Min Act: -0.0000

Data Index: 1450070 (The Pile)

Max Activating Token Index: 48

Text #3

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.7876. Min Act: 0.0000

Data Index: 1870814 (The Pile)

Max Activating Token Index: 332

Text #4

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.7513. Min Act: -0.0000

Data Index: 1291517 (The Pile)

Max Activating Token Index: 918

Text #5

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.7236. Min Act: -0.0000

Data Index: 1066311 (The Pile)

Max Activating Token Index: 992

Text #6

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.7327. Min Act: -0.0000

Data Index: 914301 (The Pile)

Max Activating Token Index: 642

Text #7

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.7356. Min Act: -0.0000

Data Index: 942367 (The Pile)

Max Activating Token Index: 439

Text #8

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.7243. Min Act: -0.0000

Data Index: 846708 (The Pile)

Max Activating Token Index: 848

Text #9

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.7288. Min Act: -0.0000

Data Index: 1267937 (The Pile)

Max Activating Token Index: 103

Text #10

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.7489. Min Act: -0.0000

Data Index: 486241 (The Pile)

Max Activating Token Index: 893

Text #11

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.7372. Min Act: -0.0000

Data Index: 810904 (The Pile)

Max Activating Token Index: 179

Text #12

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.7026. Min Act: -0.0000

Data Index: 759911 (The Pile)

Max Activating Token Index: 24

Text #13

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.6697. Min Act: -0.0000

Data Index: 1145425 (The Pile)

Max Activating Token Index: 969

Text #14

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.7166. Min Act: -0.0000

Data Index: 188892 (The Pile)

Max Activating Token Index: 981

Text #15

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.6888. Min Act: -0.0000

Data Index: 1882256 (The Pile)

Max Activating Token Index: 322

Text #16

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.6926. Min Act: -0.0000

Data Index: 1159486 (The Pile)

Max Activating Token Index: 472

Text #17

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.6446. Min Act: -0.0000

Data Index: 1577938 (The Pile)

Max Activating Token Index: 781

Text #18

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.6420. Min Act: -0.0000

Data Index: 1393172 (The Pile)

Max Activating Token Index: 412

Text #19

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.6400. Min Act: -0.0000

Data Index: 280527 (The Pile)

Max Activating Token Index: 583