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

Dataset: The Pile

Neuron 3191 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: 0.1232. Min Range: -0.1232

Max Act: 0.1232. Min Act: -0.0000

Data Index: 1619557 (The Pile)

Max Activating Token Index: 232

Text #1

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1123. Min Act: -0.0000

Data Index: 1055088 (The Pile)

Max Activating Token Index: 786

Text #2

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1091. Min Act: -0.0000

Data Index: 922654 (The Pile)

Max Activating Token Index: 1007

Text #3

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1079. Min Act: -0.0000

Data Index: 1101728 (The Pile)

Max Activating Token Index: 815

Text #4

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1165. Min Act: -0.0000

Data Index: 449419 (The Pile)

Max Activating Token Index: 331

Text #5

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1138. Min Act: -0.0000

Data Index: 1850204 (The Pile)

Max Activating Token Index: 566

Text #6

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1042. Min Act: -0.0000

Data Index: 1055609 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1069. Min Act: -0.0000

Data Index: 1407674 (The Pile)

Max Activating Token Index: 688

Text #8

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1041. Min Act: -0.0000

Data Index: 1989056 (The Pile)

Max Activating Token Index: 804

Text #9

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1023. Min Act: -0.0000

Data Index: 17240 (The Pile)

Max Activating Token Index: 545

Text #10

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1060. Min Act: -0.0000

Data Index: 982739 (The Pile)

Max Activating Token Index: 566

Text #11

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1065. Min Act: -0.0000

Data Index: 840085 (The Pile)

Max Activating Token Index: 477

Text #12

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1078. Min Act: -0.0000

Data Index: 1180365 (The Pile)

Max Activating Token Index: 850

Text #13

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1002. Min Act: -0.0000

Data Index: 766211 (The Pile)

Max Activating Token Index: 400

Text #14

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1028. Min Act: -0.0000

Data Index: 963649 (The Pile)

Max Activating Token Index: 515

Text #15

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1062. Min Act: -0.0000

Data Index: 1910928 (The Pile)

Max Activating Token Index: 50

Text #16

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1060. Min Act: -0.0000

Data Index: 733500 (The Pile)

Max Activating Token Index: 936

Text #17

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1052. Min Act: -0.0000

Data Index: 400524 (The Pile)

Max Activating Token Index: 736

Text #18

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1022. Min Act: -0.0000

Data Index: 1650730 (The Pile)

Max Activating Token Index: 1009

Text #19

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0976. Min Act: -0.0000

Data Index: 48323 (The Pile)

Max Activating Token Index: 439