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

Dataset: The Pile

Neuron 2219 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: 0.9600. Min Range: -0.9600

Max Act: 0.9600. Min Act: -0.0000

Data Index: 1536287 (The Pile)

Max Activating Token Index: 960

Text #1

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.9249. Min Act: -0.0000

Data Index: 1764517 (The Pile)

Max Activating Token Index: 643

Text #2

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.9047. Min Act: -0.0000

Data Index: 963476 (The Pile)

Max Activating Token Index: 854

Text #3

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.8702. Min Act: -0.0000

Data Index: 1332724 (The Pile)

Max Activating Token Index: 568

Text #4

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7462. Min Act: -0.0000

Data Index: 1871501 (The Pile)

Max Activating Token Index: 305

Text #5

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7526. Min Act: -0.0000

Data Index: 565729 (The Pile)

Max Activating Token Index: 885

Text #6

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7611. Min Act: -0.0000

Data Index: 957482 (The Pile)

Max Activating Token Index: 291

Text #7

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7273. Min Act: -0.0000

Data Index: 1729178 (The Pile)

Max Activating Token Index: 229

Text #8

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7156. Min Act: -0.0000

Data Index: 987641 (The Pile)

Max Activating Token Index: 898

Text #9

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.6882. Min Act: -0.0000

Data Index: 1861950 (The Pile)

Max Activating Token Index: 239

Text #10

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7061. Min Act: -0.0000

Data Index: 638371 (The Pile)

Max Activating Token Index: 922

Text #11

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.6875. Min Act: 0.0000

Data Index: 653784 (The Pile)

Max Activating Token Index: 305

Text #12

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.6402. Min Act: -0.0000

Data Index: 933933 (The Pile)

Max Activating Token Index: 456

Text #13

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.6569. Min Act: -0.0000

Data Index: 391401 (The Pile)

Max Activating Token Index: 760

Text #14

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.6343. Min Act: -0.0000

Data Index: 1807243 (The Pile)

Max Activating Token Index: 130

Text #15

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.6255. Min Act: -0.0000

Data Index: 442252 (The Pile)

Max Activating Token Index: 614

Text #16

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.6406. Min Act: -0.0000

Data Index: 878702 (The Pile)

Max Activating Token Index: 339

Text #17

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.6395. Min Act: -0.0000

Data Index: 636106 (The Pile)

Max Activating Token Index: 600

Text #18

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.6545. Min Act: -0.0000

Data Index: 1221381 (The Pile)

Max Activating Token Index: 418

Text #19

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.6409. Min Act: -0.0000

Data Index: 354243 (The Pile)

Max Activating Token Index: 141