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

Dataset: The Pile

Neuron 4898 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.9004. Min Act: -0.0000

Data Index: 397826 (The Pile)

Max Activating Token Index: 380

Text #1

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.8073. Min Act: -0.0000

Data Index: 1332533 (The Pile)

Max Activating Token Index: 745

Text #2

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.8474. Min Act: -0.0000

Data Index: 727545 (The Pile)

Max Activating Token Index: 621

Text #3

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.8113. Min Act: -0.0000

Data Index: 694184 (The Pile)

Max Activating Token Index: 569

Text #4

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.7123. Min Act: -0.0000

Data Index: 790175 (The Pile)

Max Activating Token Index: 630

Text #5

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.7448. Min Act: -0.0000

Data Index: 1800715 (The Pile)

Max Activating Token Index: 290

Text #6

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.7476. Min Act: -0.0000

Data Index: 667955 (The Pile)

Max Activating Token Index: 873

Text #7

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.7318. Min Act: -0.0000

Data Index: 43636 (The Pile)

Max Activating Token Index: 931

Text #8

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.7198. Min Act: -0.0000

Data Index: 1474389 (The Pile)

Max Activating Token Index: 442

Text #9

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.7263. Min Act: -0.0000

Data Index: 171044 (The Pile)

Max Activating Token Index: 319

Text #10

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.6551. Min Act: -0.0000

Data Index: 329111 (The Pile)

Max Activating Token Index: 215

Text #11

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.6084. Min Act: -0.0000

Data Index: 530169 (The Pile)

Max Activating Token Index: 845

Text #12

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.6479. Min Act: -0.0000

Data Index: 1128350 (The Pile)

Max Activating Token Index: 1007

Text #13

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.6532. Min Act: -0.0000

Data Index: 1768900 (The Pile)

Max Activating Token Index: 737

Text #14

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.6817. Min Act: -0.0000

Data Index: 1008525 (The Pile)

Max Activating Token Index: 608

Text #15

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.6120. Min Act: -0.0000

Data Index: 1038213 (The Pile)

Max Activating Token Index: 883

Text #16

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.6327. Min Act: -0.0000

Data Index: 1003231 (The Pile)

Max Activating Token Index: 413

Text #17

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.5972. Min Act: -0.0000

Data Index: 1336087 (The Pile)

Max Activating Token Index: 200

Text #18

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.6268. Min Act: -0.0000

Data Index: 539668 (The Pile)

Max Activating Token Index: 803

Text #19

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.6763. Min Act: -0.0000

Data Index: 185751 (The Pile)

Max Activating Token Index: 274