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

Dataset: The Pile

Neuron 1556 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: 1.8536. Min Range: -1.8536

Max Act: 1.8536. Min Act: -0.0000

Data Index: 1049381 (The Pile)

Max Activating Token Index: 456

Text #1

Max Range: 1.8536. Min Range: -1.8536

Max Act: 1.7952. Min Act: -0.0000

Data Index: 777015 (The Pile)

Max Activating Token Index: 355

Text #2

Max Range: 1.8536. Min Range: -1.8536

Max Act: 1.5762. Min Act: -0.0000

Data Index: 196602 (The Pile)

Max Activating Token Index: 108

Text #3

Max Range: 1.8536. Min Range: -1.8536

Max Act: 1.6747. Min Act: -0.0000

Data Index: 146406 (The Pile)

Max Activating Token Index: 62

Text #4

Max Range: 1.8536. Min Range: -1.8536

Max Act: 1.7047. Min Act: -0.0000

Data Index: 1734914 (The Pile)

Max Activating Token Index: 114

Text #5

Max Range: 1.8536. Min Range: -1.8536

Max Act: 1.5550. Min Act: -0.0000

Data Index: 1007883 (The Pile)

Max Activating Token Index: 288

Text #6

Max Range: 1.8536. Min Range: -1.8536

Max Act: 1.7031. Min Act: -0.0000

Data Index: 485899 (The Pile)

Max Activating Token Index: 1019

Text #7

Max Range: 1.8536. Min Range: -1.8536

Max Act: 1.6224. Min Act: -0.0000

Data Index: 569994 (The Pile)

Max Activating Token Index: 979

Text #8

Max Range: 1.8536. Min Range: -1.8536

Max Act: 1.5529. Min Act: -0.0000

Data Index: 1992335 (The Pile)

Max Activating Token Index: 510

Text #9

Max Range: 1.8536. Min Range: -1.8536

Max Act: 1.5458. Min Act: -0.0000

Data Index: 1733893 (The Pile)

Max Activating Token Index: 531

Text #10

Max Range: 1.8536. Min Range: -1.8536

Max Act: 1.4544. Min Act: -0.0000

Data Index: 1668281 (The Pile)

Max Activating Token Index: 786

Text #11

Max Range: 1.8536. Min Range: -1.8536

Max Act: 1.5886. Min Act: -0.0000

Data Index: 1637618 (The Pile)

Max Activating Token Index: 901

Text #12

Max Range: 1.8536. Min Range: -1.8536

Max Act: 1.6336. Min Act: -0.0000

Data Index: 125406 (The Pile)

Max Activating Token Index: 1009

Text #13

Max Range: 1.8536. Min Range: -1.8536

Max Act: 1.4745. Min Act: -0.0000

Data Index: 1672674 (The Pile)

Max Activating Token Index: 150

Text #14

Max Range: 1.8536. Min Range: -1.8536

Max Act: 1.4132. Min Act: -0.0000

Data Index: 1656363 (The Pile)

Max Activating Token Index: 731

Text #15

Max Range: 1.8536. Min Range: -1.8536

Max Act: 1.3765. Min Act: -0.0000

Data Index: 1263725 (The Pile)

Max Activating Token Index: 974

Text #16

Max Range: 1.8536. Min Range: -1.8536

Max Act: 1.4506. Min Act: -0.0000

Data Index: 662715 (The Pile)

Max Activating Token Index: 413

Text #17

Max Range: 1.8536. Min Range: -1.8536

Max Act: 1.5522. Min Act: -0.0000

Data Index: 842680 (The Pile)

Max Activating Token Index: 966

Text #18

Max Range: 1.8536. Min Range: -1.8536

Max Act: 1.6127. Min Act: -0.0000

Data Index: 1310327 (The Pile)

Max Activating Token Index: 870

Text #19

Max Range: 1.8536. Min Range: -1.8536

Max Act: 1.3607. Min Act: -0.0000

Data Index: 1485889 (The Pile)

Max Activating Token Index: 979