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

Dataset: The Pile

Neuron 5096 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3432. Min Range: -4.3432

Max Act: 4.3432. Min Act: -0.0000

Data Index: 551904 (The Pile)

Max Activating Token Index: 389

Text #1

Max Range: 4.3432. Min Range: -4.3432

Max Act: 4.2240. Min Act: -0.0000

Data Index: 261840 (The Pile)

Max Activating Token Index: 212

Text #2

Max Range: 4.3432. Min Range: -4.3432

Max Act: 3.7860. Min Act: -0.0000

Data Index: 1781463 (The Pile)

Max Activating Token Index: 532

Text #3

Max Range: 4.3432. Min Range: -4.3432

Max Act: 3.6685. Min Act: -0.0000

Data Index: 1157771 (The Pile)

Max Activating Token Index: 601

Text #4

Max Range: 4.3432. Min Range: -4.3432

Max Act: 3.7224. Min Act: -0.0000

Data Index: 1284879 (The Pile)

Max Activating Token Index: 589

Text #5

Max Range: 4.3432. Min Range: -4.3432

Max Act: 3.6699. Min Act: -0.0000

Data Index: 117330 (The Pile)

Max Activating Token Index: 736

Text #6

Max Range: 4.3432. Min Range: -4.3432

Max Act: 3.5249. Min Act: -0.0000

Data Index: 1030341 (The Pile)

Max Activating Token Index: 410

Text #7

Max Range: 4.3432. Min Range: -4.3432

Max Act: 3.6574. Min Act: -0.0000

Data Index: 1281222 (The Pile)

Max Activating Token Index: 987

Text #8

Max Range: 4.3432. Min Range: -4.3432

Max Act: 3.6406. Min Act: -0.0000

Data Index: 1032699 (The Pile)

Max Activating Token Index: 24

Text #9

Max Range: 4.3432. Min Range: -4.3432

Max Act: 3.4553. Min Act: -0.0000

Data Index: 995020 (The Pile)

Max Activating Token Index: 326

Text #10

Max Range: 4.3432. Min Range: -4.3432

Max Act: 3.5415. Min Act: -0.0000

Data Index: 31605 (The Pile)

Max Activating Token Index: 366

Text #11

Max Range: 4.3432. Min Range: -4.3432

Max Act: 3.6676. Min Act: -0.0000

Data Index: 1900629 (The Pile)

Max Activating Token Index: 377

Text #12

Max Range: 4.3432. Min Range: -4.3432

Max Act: 3.4771. Min Act: -0.0000

Data Index: 1361605 (The Pile)

Max Activating Token Index: 83

Text #13

Max Range: 4.3432. Min Range: -4.3432

Max Act: 3.4414. Min Act: -0.0000

Data Index: 1937714 (The Pile)

Max Activating Token Index: 584

Text #14

Max Range: 4.3432. Min Range: -4.3432

Max Act: 3.2598. Min Act: -0.0000

Data Index: 1892615 (The Pile)

Max Activating Token Index: 713

Text #15

Max Range: 4.3432. Min Range: -4.3432

Max Act: 3.4130. Min Act: -0.0000

Data Index: 197816 (The Pile)

Max Activating Token Index: 290

Text #16

Max Range: 4.3432. Min Range: -4.3432

Max Act: 3.2397. Min Act: -0.0000

Data Index: 715616 (The Pile)

Max Activating Token Index: 298

Text #17

Max Range: 4.3432. Min Range: -4.3432

Max Act: 3.3847. Min Act: -0.0000

Data Index: 865306 (The Pile)

Max Activating Token Index: 359

Text #18

Max Range: 4.3432. Min Range: -4.3432

Max Act: 3.3497. Min Act: -0.0000

Data Index: 1893801 (The Pile)

Max Activating Token Index: 444

Text #19

Max Range: 4.3432. Min Range: -4.3432

Max Act: 3.2066. Min Act: -0.0000

Data Index: 498302 (The Pile)

Max Activating Token Index: 988