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

Dataset: The Pile

Neuron 3132 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: 0.1684. Min Range: -0.1684

Max Act: 0.1448. Min Act: -0.0000

Data Index: 1360116 (The Pile)

Max Activating Token Index: 893

Text #1

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1621. Min Act: -0.0000

Data Index: 271927 (The Pile)

Max Activating Token Index: 713

Text #2

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1285. Min Act: -0.0000

Data Index: 1184716 (The Pile)

Max Activating Token Index: 396

Text #3

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1684. Min Act: -0.0000

Data Index: 1143919 (The Pile)

Max Activating Token Index: 571

Text #4

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1232. Min Act: -0.0000

Data Index: 1095352 (The Pile)

Max Activating Token Index: 864

Text #5

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1114. Min Act: -0.0000

Data Index: 1579649 (The Pile)

Max Activating Token Index: 195

Text #6

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1151. Min Act: -0.0000

Data Index: 1032450 (The Pile)

Max Activating Token Index: 354

Text #7

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1154. Min Act: -0.0000

Data Index: 839342 (The Pile)

Max Activating Token Index: 345

Text #8

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1140. Min Act: -0.0000

Data Index: 774398 (The Pile)

Max Activating Token Index: 659

Text #9

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1127. Min Act: -0.0000

Data Index: 776105 (The Pile)

Max Activating Token Index: 301

Text #10

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1070. Min Act: -0.0000

Data Index: 1508563 (The Pile)

Max Activating Token Index: 356

Text #11

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1086. Min Act: -0.0000

Data Index: 1261539 (The Pile)

Max Activating Token Index: 1020

Text #12

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.0994. Min Act: -0.0000

Data Index: 1902948 (The Pile)

Max Activating Token Index: 680

Text #13

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.0989. Min Act: -0.0000

Data Index: 1188960 (The Pile)

Max Activating Token Index: 795

Text #14

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1065. Min Act: -0.0000

Data Index: 1150282 (The Pile)

Max Activating Token Index: 298

Text #15

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1098. Min Act: -0.0000

Data Index: 1030514 (The Pile)

Max Activating Token Index: 480

Text #16

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1045. Min Act: -0.0000

Data Index: 1730373 (The Pile)

Max Activating Token Index: 630

Text #17

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1076. Min Act: -0.0000

Data Index: 872524 (The Pile)

Max Activating Token Index: 944

Text #18

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1031. Min Act: -0.0000

Data Index: 279072 (The Pile)

Max Activating Token Index: 321

Text #19

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1016. Min Act: -0.0000

Data Index: 1403592 (The Pile)

Max Activating Token Index: 877