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

Dataset: The Pile

Neuron 4730 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9717. Min Range: -1.9717

Max Act: 1.9492. Min Act: 0.0000

Data Index: 622547 (The Pile)

Max Activating Token Index: 510

Text #1

Max Range: 1.9717. Min Range: -1.9717

Max Act: 1.7425. Min Act: -0.0000

Data Index: 404236 (The Pile)

Max Activating Token Index: 606

Text #2

Max Range: 1.9717. Min Range: -1.9717

Max Act: 1.9717. Min Act: -0.0000

Data Index: 725920 (The Pile)

Max Activating Token Index: 64

Text #3

Max Range: 1.9717. Min Range: -1.9717

Max Act: 1.3847. Min Act: -0.0000

Data Index: 446434 (The Pile)

Max Activating Token Index: 256

Text #4

Max Range: 1.9717. Min Range: -1.9717

Max Act: 1.4338. Min Act: -0.0000

Data Index: 823220 (The Pile)

Max Activating Token Index: 776

Text #5

Max Range: 1.9717. Min Range: -1.9717

Max Act: 1.5105. Min Act: -0.0000

Data Index: 1279286 (The Pile)

Max Activating Token Index: 861

Text #6

Max Range: 1.9717. Min Range: -1.9717

Max Act: 1.6579. Min Act: -0.0000

Data Index: 1314942 (The Pile)

Max Activating Token Index: 200

Text #7

Max Range: 1.9717. Min Range: -1.9717

Max Act: 1.5351. Min Act: -0.0000

Data Index: 1656778 (The Pile)

Max Activating Token Index: 116

Text #8

Max Range: 1.9717. Min Range: -1.9717

Max Act: 1.5246. Min Act: -0.0000

Data Index: 22398 (The Pile)

Max Activating Token Index: 353

Text #9

Max Range: 1.9717. Min Range: -1.9717

Max Act: 1.5276. Min Act: -0.0000

Data Index: 1030363 (The Pile)

Max Activating Token Index: 729

Text #10

Max Range: 1.9717. Min Range: -1.9717

Max Act: 1.4930. Min Act: -0.0000

Data Index: 1012330 (The Pile)

Max Activating Token Index: 204

Text #11

Max Range: 1.9717. Min Range: -1.9717

Max Act: 1.4028. Min Act: -0.0000

Data Index: 308886 (The Pile)

Max Activating Token Index: 559

Text #12

Max Range: 1.9717. Min Range: -1.9717

Max Act: 1.3008. Min Act: 0.0000

Data Index: 856731 (The Pile)

Max Activating Token Index: 250

Text #13

Max Range: 1.9717. Min Range: -1.9717

Max Act: 1.3274. Min Act: -0.0000

Data Index: 1829442 (The Pile)

Max Activating Token Index: 267

Text #14

Max Range: 1.9717. Min Range: -1.9717

Max Act: 1.7571. Min Act: -0.0000

Data Index: 1088304 (The Pile)

Max Activating Token Index: 845

Text #15

Max Range: 1.9717. Min Range: -1.9717

Max Act: 1.4989. Min Act: -0.0000

Data Index: 379725 (The Pile)

Max Activating Token Index: 749

Text #16

Max Range: 1.9717. Min Range: -1.9717

Max Act: 1.4553. Min Act: -0.0000

Data Index: 1577331 (The Pile)

Max Activating Token Index: 648

Text #17

Max Range: 1.9717. Min Range: -1.9717

Max Act: 1.5342. Min Act: -0.0000

Data Index: 762580 (The Pile)

Max Activating Token Index: 377

Text #18

Max Range: 1.9717. Min Range: -1.9717

Max Act: 1.3707. Min Act: -0.0000

Data Index: 96453 (The Pile)

Max Activating Token Index: 775

Text #19

Max Range: 1.9717. Min Range: -1.9717

Max Act: 1.1866. Min Act: -0.0000

Data Index: 1798603 (The Pile)

Max Activating Token Index: 809