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

Dataset: The Pile

Neuron 1721 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.6512. Min Act: -0.0000

Data Index: 1930922 (The Pile)

Max Activating Token Index: 403

Text #1

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.6127. Min Act: -0.0000

Data Index: 1324333 (The Pile)

Max Activating Token Index: 95

Text #2

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.6178. Min Act: -0.0000

Data Index: 162983 (The Pile)

Max Activating Token Index: 944

Text #3

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.5846. Min Act: -0.0000

Data Index: 1664830 (The Pile)

Max Activating Token Index: 518

Text #4

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.5623. Min Act: -0.0000

Data Index: 1233730 (The Pile)

Max Activating Token Index: 962

Text #5

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.5642. Min Act: -0.0000

Data Index: 728791 (The Pile)

Max Activating Token Index: 544

Text #6

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.5513. Min Act: -0.0000

Data Index: 1290687 (The Pile)

Max Activating Token Index: 895

Text #7

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.5519. Min Act: -0.0000

Data Index: 1158438 (The Pile)

Max Activating Token Index: 40

Text #8

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.5109. Min Act: -0.0000

Data Index: 314030 (The Pile)

Max Activating Token Index: 1009

Text #9

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.5510. Min Act: -0.0000

Data Index: 1263984 (The Pile)

Max Activating Token Index: 943

Text #10

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.4940. Min Act: -0.0000

Data Index: 1736968 (The Pile)

Max Activating Token Index: 936

Text #11

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.4720. Min Act: -0.0000

Data Index: 858581 (The Pile)

Max Activating Token Index: 220

Text #12

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.6402. Min Act: -0.0000

Data Index: 637301 (The Pile)

Max Activating Token Index: 962

Text #13

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.4937. Min Act: -0.0000

Data Index: 918702 (The Pile)

Max Activating Token Index: 355

Text #14

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.4368. Min Act: -0.0000

Data Index: 609103 (The Pile)

Max Activating Token Index: 627

Text #15

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.5132. Min Act: -0.0000

Data Index: 1191100 (The Pile)

Max Activating Token Index: 175

Text #16

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.4786. Min Act: -0.0000

Data Index: 1277320 (The Pile)

Max Activating Token Index: 141

Text #17

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.4702. Min Act: -0.0000

Data Index: 1145568 (The Pile)

Max Activating Token Index: 967

Text #18

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.4898. Min Act: -0.0000

Data Index: 30898 (The Pile)

Max Activating Token Index: 60

Text #19

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.4890. Min Act: -0.0000

Data Index: 368289 (The Pile)

Max Activating Token Index: 898