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

Dataset: The Pile

Neuron 4604 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9944. Min Range: -1.9944

Max Act: 1.9944. Min Act: -0.0000

Data Index: 358017 (The Pile)

Max Activating Token Index: 433

Text #1

Max Range: 1.9944. Min Range: -1.9944

Max Act: 1.8045. Min Act: -0.0000

Data Index: 504986 (The Pile)

Max Activating Token Index: 936

Text #2

Max Range: 1.9944. Min Range: -1.9944

Max Act: 1.8820. Min Act: -0.0000

Data Index: 1701222 (The Pile)

Max Activating Token Index: 686

Text #3

Max Range: 1.9944. Min Range: -1.9944

Max Act: 1.7414. Min Act: -0.0000

Data Index: 1948994 (The Pile)

Max Activating Token Index: 239

Text #4

Max Range: 1.9944. Min Range: -1.9944

Max Act: 1.7740. Min Act: -0.0000

Data Index: 1918943 (The Pile)

Max Activating Token Index: 247

Text #5

Max Range: 1.9944. Min Range: -1.9944

Max Act: 1.7340. Min Act: -0.0000

Data Index: 964528 (The Pile)

Max Activating Token Index: 399

Text #6

Max Range: 1.9944. Min Range: -1.9944

Max Act: 1.6223. Min Act: -0.0000

Data Index: 811477 (The Pile)

Max Activating Token Index: 693

Text #7

Max Range: 1.9944. Min Range: -1.9944

Max Act: 1.6674. Min Act: -0.0000

Data Index: 1108400 (The Pile)

Max Activating Token Index: 420

Text #8

Max Range: 1.9944. Min Range: -1.9944

Max Act: 1.6647. Min Act: -0.0000

Data Index: 536020 (The Pile)

Max Activating Token Index: 443

Text #9

Max Range: 1.9944. Min Range: -1.9944

Max Act: 1.4655. Min Act: -0.0000

Data Index: 1893948 (The Pile)

Max Activating Token Index: 870

Text #10

Max Range: 1.9944. Min Range: -1.9944

Max Act: 1.7328. Min Act: -0.0000

Data Index: 1589489 (The Pile)

Max Activating Token Index: 989

Text #11

Max Range: 1.9944. Min Range: -1.9944

Max Act: 1.6102. Min Act: -0.0000

Data Index: 1775112 (The Pile)

Max Activating Token Index: 759

Text #12

Max Range: 1.9944. Min Range: -1.9944

Max Act: 1.5934. Min Act: -0.0000

Data Index: 350483 (The Pile)

Max Activating Token Index: 622

Text #13

Max Range: 1.9944. Min Range: -1.9944

Max Act: 1.4763. Min Act: -0.0000

Data Index: 642197 (The Pile)

Max Activating Token Index: 356

Text #14

Max Range: 1.9944. Min Range: -1.9944

Max Act: 1.5165. Min Act: -0.0000

Data Index: 911565 (The Pile)

Max Activating Token Index: 73

Text #15

Max Range: 1.9944. Min Range: -1.9944

Max Act: 1.3367. Min Act: -0.0000

Data Index: 1281071 (The Pile)

Max Activating Token Index: 1020

Text #16

Max Range: 1.9944. Min Range: -1.9944

Max Act: 1.5081. Min Act: -0.0000

Data Index: 372579 (The Pile)

Max Activating Token Index: 246

Text #17

Max Range: 1.9944. Min Range: -1.9944

Max Act: 1.4957. Min Act: -0.0000

Data Index: 319739 (The Pile)

Max Activating Token Index: 413

Text #18

Max Range: 1.9944. Min Range: -1.9944

Max Act: 1.6255. Min Act: -0.0000

Data Index: 1977695 (The Pile)

Max Activating Token Index: 185

Text #19

Max Range: 1.9944. Min Range: -1.9944

Max Act: 1.3494. Min Act: -0.0000

Data Index: 1279069 (The Pile)

Max Activating Token Index: 830