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

Dataset: The Pile

Neuron 4445 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8632. Min Range: -1.8632

Max Act: 1.6423. Min Act: -0.0000

Data Index: 1430197 (The Pile)

Max Activating Token Index: 572

Text #1

Max Range: 1.8632. Min Range: -1.8632

Max Act: 1.6325. Min Act: -0.0000

Data Index: 1900125 (The Pile)

Max Activating Token Index: 542

Text #2

Max Range: 1.8632. Min Range: -1.8632

Max Act: 1.8632. Min Act: -0.0000

Data Index: 1714158 (The Pile)

Max Activating Token Index: 627

Text #3

Max Range: 1.8632. Min Range: -1.8632

Max Act: 1.3940. Min Act: -0.0000

Data Index: 1635375 (The Pile)

Max Activating Token Index: 662

Text #4

Max Range: 1.8632. Min Range: -1.8632

Max Act: 1.5935. Min Act: -0.0000

Data Index: 830979 (The Pile)

Max Activating Token Index: 529

Text #5

Max Range: 1.8632. Min Range: -1.8632

Max Act: 1.2863. Min Act: -0.0000

Data Index: 1382868 (The Pile)

Max Activating Token Index: 211

Text #6

Max Range: 1.8632. Min Range: -1.8632

Max Act: 1.4234. Min Act: -0.0000

Data Index: 1958115 (The Pile)

Max Activating Token Index: 424

Text #7

Max Range: 1.8632. Min Range: -1.8632

Max Act: 1.3772. Min Act: -0.0000

Data Index: 779864 (The Pile)

Max Activating Token Index: 523

Text #8

Max Range: 1.8632. Min Range: -1.8632

Max Act: 1.3837. Min Act: -0.0000

Data Index: 934559 (The Pile)

Max Activating Token Index: 315

Text #9

Max Range: 1.8632. Min Range: -1.8632

Max Act: 1.5881. Min Act: -0.0000

Data Index: 618094 (The Pile)

Max Activating Token Index: 896

Text #10

Max Range: 1.8632. Min Range: -1.8632

Max Act: 1.4515. Min Act: -0.0000

Data Index: 267085 (The Pile)

Max Activating Token Index: 594

Text #11

Max Range: 1.8632. Min Range: -1.8632

Max Act: 1.3999. Min Act: -0.0000

Data Index: 1829696 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 1.8632. Min Range: -1.8632

Max Act: 1.2140. Min Act: -0.0000

Data Index: 1241788 (The Pile)

Max Activating Token Index: 631

Text #13

Max Range: 1.8632. Min Range: -1.8632

Max Act: 1.2989. Min Act: -0.0000

Data Index: 593814 (The Pile)

Max Activating Token Index: 422

Text #14

Max Range: 1.8632. Min Range: -1.8632

Max Act: 1.4696. Min Act: -0.0000

Data Index: 985644 (The Pile)

Max Activating Token Index: 589

Text #15

Max Range: 1.8632. Min Range: -1.8632

Max Act: 1.2681. Min Act: -0.0000

Data Index: 546325 (The Pile)

Max Activating Token Index: 265

Text #16

Max Range: 1.8632. Min Range: -1.8632

Max Act: 1.2573. Min Act: -0.0000

Data Index: 763402 (The Pile)

Max Activating Token Index: 696

Text #17

Max Range: 1.8632. Min Range: -1.8632

Max Act: 1.2433. Min Act: 0.0000

Data Index: 175453 (The Pile)

Max Activating Token Index: 344

Text #18

Max Range: 1.8632. Min Range: -1.8632

Max Act: 1.2672. Min Act: -0.0000

Data Index: 1122159 (The Pile)

Max Activating Token Index: 468

Text #19

Max Range: 1.8632. Min Range: -1.8632

Max Act: 1.1470. Min Act: -0.0000

Data Index: 1648661 (The Pile)

Max Activating Token Index: 735