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

Dataset: The Pile

Neuron 1946 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1088. Min Range: -1.1088

Max Act: 1.1088. Min Act: -0.0000

Data Index: 1217790 (The Pile)

Max Activating Token Index: 690

Text #1

Max Range: 1.1088. Min Range: -1.1088

Max Act: 0.8970. Min Act: -0.0000

Data Index: 110229 (The Pile)

Max Activating Token Index: 68

Text #2

Max Range: 1.1088. Min Range: -1.1088

Max Act: 0.7915. Min Act: -0.0000

Data Index: 258160 (The Pile)

Max Activating Token Index: 879

Text #3

Max Range: 1.1088. Min Range: -1.1088

Max Act: 0.7588. Min Act: -0.0000

Data Index: 1670943 (The Pile)

Max Activating Token Index: 814

Text #4

Max Range: 1.1088. Min Range: -1.1088

Max Act: 0.6908. Min Act: -0.0000

Data Index: 1153020 (The Pile)

Max Activating Token Index: 512

Text #5

Max Range: 1.1088. Min Range: -1.1088

Max Act: 0.7197. Min Act: -0.0000

Data Index: 1069454 (The Pile)

Max Activating Token Index: 279

Text #6

Max Range: 1.1088. Min Range: -1.1088

Max Act: 0.7092. Min Act: -0.0000

Data Index: 165062 (The Pile)

Max Activating Token Index: 200

Text #7

Max Range: 1.1088. Min Range: -1.1088

Max Act: 0.6694. Min Act: -0.0000

Data Index: 1932609 (The Pile)

Max Activating Token Index: 138

Text #8

Max Range: 1.1088. Min Range: -1.1088

Max Act: 0.6998. Min Act: -0.0000

Data Index: 1560478 (The Pile)

Max Activating Token Index: 779

Text #9

Max Range: 1.1088. Min Range: -1.1088

Max Act: 0.6295. Min Act: -0.0000

Data Index: 1526544 (The Pile)

Max Activating Token Index: 502

Text #10

Max Range: 1.1088. Min Range: -1.1088

Max Act: 0.6137. Min Act: -0.0000

Data Index: 434909 (The Pile)

Max Activating Token Index: 973

Text #11

Max Range: 1.1088. Min Range: -1.1088

Max Act: 0.5959. Min Act: -0.0000

Data Index: 579508 (The Pile)

Max Activating Token Index: 256

Text #12

Max Range: 1.1088. Min Range: -1.1088

Max Act: 0.5917. Min Act: -0.0000

Data Index: 1989311 (The Pile)

Max Activating Token Index: 450

Text #13

Max Range: 1.1088. Min Range: -1.1088

Max Act: 0.5678. Min Act: -0.0000

Data Index: 1599052 (The Pile)

Max Activating Token Index: 702

Text #14

Max Range: 1.1088. Min Range: -1.1088

Max Act: 0.5873. Min Act: -0.0000

Data Index: 210832 (The Pile)

Max Activating Token Index: 267

Text #15

Max Range: 1.1088. Min Range: -1.1088

Max Act: 0.5732. Min Act: -0.0000

Data Index: 947106 (The Pile)

Max Activating Token Index: 297

Text #16

Max Range: 1.1088. Min Range: -1.1088

Max Act: 0.5893. Min Act: -0.0000

Data Index: 1350377 (The Pile)

Max Activating Token Index: 13

Text #17

Max Range: 1.1088. Min Range: -1.1088

Max Act: 0.5837. Min Act: -0.0000

Data Index: 166839 (The Pile)

Max Activating Token Index: 98

Text #18

Max Range: 1.1088. Min Range: -1.1088

Max Act: 0.5475. Min Act: -0.0000

Data Index: 756540 (The Pile)

Max Activating Token Index: 782

Text #19

Max Range: 1.1088. Min Range: -1.1088

Max Act: 0.5223. Min Act: -0.0000

Data Index: 1723173 (The Pile)

Max Activating Token Index: 612