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

Dataset: The Pile

Neuron 3456 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: 1.3083. Min Range: -1.3083

Max Act: 1.3083. Min Act: -0.0000

Data Index: 1595655 (The Pile)

Max Activating Token Index: 523

Text #1

Max Range: 1.3083. Min Range: -1.3083

Max Act: 1.1705. Min Act: -0.0000

Data Index: 76707 (The Pile)

Max Activating Token Index: 227

Text #2

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.9498. Min Act: -0.0000

Data Index: 953092 (The Pile)

Max Activating Token Index: 552

Text #3

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.9002. Min Act: -0.0000

Data Index: 1122783 (The Pile)

Max Activating Token Index: 972

Text #4

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.9399. Min Act: -0.0000

Data Index: 1156184 (The Pile)

Max Activating Token Index: 944

Text #5

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.9396. Min Act: -0.0000

Data Index: 1288185 (The Pile)

Max Activating Token Index: 319

Text #6

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.9044. Min Act: -0.0000

Data Index: 793671 (The Pile)

Max Activating Token Index: 452

Text #7

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.9503. Min Act: -0.0000

Data Index: 15170 (The Pile)

Max Activating Token Index: 77

Text #8

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.9950. Min Act: -0.0000

Data Index: 980758 (The Pile)

Max Activating Token Index: 774

Text #9

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.8920. Min Act: -0.0000

Data Index: 1480554 (The Pile)

Max Activating Token Index: 791

Text #10

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.8911. Min Act: -0.0000

Data Index: 1617052 (The Pile)

Max Activating Token Index: 962

Text #11

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.8853. Min Act: -0.0000

Data Index: 283345 (The Pile)

Max Activating Token Index: 329

Text #12

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.9281. Min Act: -0.0000

Data Index: 385966 (The Pile)

Max Activating Token Index: 883

Text #13

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.7564. Min Act: -0.0000

Data Index: 514967 (The Pile)

Max Activating Token Index: 867

Text #14

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.8509. Min Act: -0.0000

Data Index: 744850 (The Pile)

Max Activating Token Index: 500

Text #15

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.7970. Min Act: -0.0000

Data Index: 1727383 (The Pile)

Max Activating Token Index: 881

Text #16

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.8449. Min Act: -0.0000

Data Index: 1376639 (The Pile)

Max Activating Token Index: 509

Text #17

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.8470. Min Act: -0.0000

Data Index: 803140 (The Pile)

Max Activating Token Index: 736

Text #18

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.7822. Min Act: -0.0000

Data Index: 1893524 (The Pile)

Max Activating Token Index: 706

Text #19

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.8261. Min Act: -0.0000

Data Index: 1248990 (The Pile)

Max Activating Token Index: 287