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

Dataset: The Pile

Neuron 989 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: 0.9531. Min Range: -0.9531

Max Act: 0.9531. Min Act: -0.0000

Data Index: 1144691 (The Pile)

Max Activating Token Index: 551

Text #1

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.9206. Min Act: -0.0000

Data Index: 246605 (The Pile)

Max Activating Token Index: 695

Text #2

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8881. Min Act: -0.0000

Data Index: 1007491 (The Pile)

Max Activating Token Index: 859

Text #3

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.9024. Min Act: -0.0000

Data Index: 483908 (The Pile)

Max Activating Token Index: 366

Text #4

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8433. Min Act: -0.0000

Data Index: 1651136 (The Pile)

Max Activating Token Index: 558

Text #5

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.7946. Min Act: -0.0000

Data Index: 571602 (The Pile)

Max Activating Token Index: 309

Text #6

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.7971. Min Act: -0.0000

Data Index: 1737161 (The Pile)

Max Activating Token Index: 980

Text #7

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8580. Min Act: -0.0000

Data Index: 1434539 (The Pile)

Max Activating Token Index: 10

Text #8

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8622. Min Act: -0.0000

Data Index: 1916503 (The Pile)

Max Activating Token Index: 834

Text #9

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8311. Min Act: -0.0000

Data Index: 1617828 (The Pile)

Max Activating Token Index: 792

Text #10

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8442. Min Act: -0.0000

Data Index: 226669 (The Pile)

Max Activating Token Index: 463

Text #11

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8309. Min Act: -0.0000

Data Index: 532814 (The Pile)

Max Activating Token Index: 731

Text #12

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8259. Min Act: -0.0000

Data Index: 896206 (The Pile)

Max Activating Token Index: 429

Text #13

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.7749. Min Act: -0.0000

Data Index: 900412 (The Pile)

Max Activating Token Index: 696

Text #14

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8172. Min Act: -0.0000

Data Index: 688152 (The Pile)

Max Activating Token Index: 430

Text #15

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.7769. Min Act: -0.0000

Data Index: 290956 (The Pile)

Max Activating Token Index: 640

Text #16

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.7433. Min Act: -0.0000

Data Index: 1504311 (The Pile)

Max Activating Token Index: 265

Text #17

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8385. Min Act: -0.0000

Data Index: 1069368 (The Pile)

Max Activating Token Index: 455

Text #18

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8097. Min Act: -0.0000

Data Index: 1352257 (The Pile)

Max Activating Token Index: 356

Text #19

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8244. Min Act: -0.0000

Data Index: 591626 (The Pile)

Max Activating Token Index: 815