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

Dataset: The Pile

Neuron 1565 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: 0.6238. Min Range: -0.6238

Max Act: 0.6238. Min Act: -0.0000

Data Index: 1480646 (The Pile)

Max Activating Token Index: 666

Text #1

Max Range: 0.6238. Min Range: -0.6238

Max Act: 0.4517. Min Act: -0.0000

Data Index: 65473 (The Pile)

Max Activating Token Index: 330

Text #2

Max Range: 0.6238. Min Range: -0.6238

Max Act: 0.4287. Min Act: -0.0000

Data Index: 1651100 (The Pile)

Max Activating Token Index: 586

Text #3

Max Range: 0.6238. Min Range: -0.6238

Max Act: 0.4085. Min Act: -0.0000

Data Index: 708440 (The Pile)

Max Activating Token Index: 292

Text #4

Max Range: 0.6238. Min Range: -0.6238

Max Act: 0.3890. Min Act: -0.0000

Data Index: 80646 (The Pile)

Max Activating Token Index: 138

Text #5

Max Range: 0.6238. Min Range: -0.6238

Max Act: 0.3866. Min Act: -0.0000

Data Index: 51429 (The Pile)

Max Activating Token Index: 523

Text #6

Max Range: 0.6238. Min Range: -0.6238

Max Act: 0.3450. Min Act: -0.0000

Data Index: 626741 (The Pile)

Max Activating Token Index: 797

Text #7

Max Range: 0.6238. Min Range: -0.6238

Max Act: 0.3702. Min Act: -0.0000

Data Index: 805791 (The Pile)

Max Activating Token Index: 273

Text #8

Max Range: 0.6238. Min Range: -0.6238

Max Act: 0.4263. Min Act: -0.0000

Data Index: 704143 (The Pile)

Max Activating Token Index: 554

Text #9

Max Range: 0.6238. Min Range: -0.6238

Max Act: 0.4018. Min Act: -0.0000

Data Index: 1928680 (The Pile)

Max Activating Token Index: 464

Text #10

Max Range: 0.6238. Min Range: -0.6238

Max Act: 0.3769. Min Act: -0.0000

Data Index: 59967 (The Pile)

Max Activating Token Index: 982

Text #11

Max Range: 0.6238. Min Range: -0.6238

Max Act: 0.3401. Min Act: -0.0000

Data Index: 446480 (The Pile)

Max Activating Token Index: 709

Text #12

Max Range: 0.6238. Min Range: -0.6238

Max Act: 0.3672. Min Act: -0.0000

Data Index: 144693 (The Pile)

Max Activating Token Index: 175

Text #13

Max Range: 0.6238. Min Range: -0.6238

Max Act: 0.3291. Min Act: -0.0000

Data Index: 1118952 (The Pile)

Max Activating Token Index: 579

Text #14

Max Range: 0.6238. Min Range: -0.6238

Max Act: 0.4506. Min Act: -0.0000

Data Index: 919430 (The Pile)

Max Activating Token Index: 970

Text #15

Max Range: 0.6238. Min Range: -0.6238

Max Act: 0.3611. Min Act: -0.0000

Data Index: 1415318 (The Pile)

Max Activating Token Index: 749

Text #16

Max Range: 0.6238. Min Range: -0.6238

Max Act: 0.3019. Min Act: -0.0000

Data Index: 1258090 (The Pile)

Max Activating Token Index: 503

Text #17

Max Range: 0.6238. Min Range: -0.6238

Max Act: 0.2818. Min Act: -0.0000

Data Index: 1607426 (The Pile)

Max Activating Token Index: 694

Text #18

Max Range: 0.6238. Min Range: -0.6238

Max Act: 0.3330. Min Act: -0.0000

Data Index: 1251417 (The Pile)

Max Activating Token Index: 305

Text #19

Max Range: 0.6238. Min Range: -0.6238

Max Act: 0.2995. Min Act: -0.0000

Data Index: 1746692 (The Pile)

Max Activating Token Index: 270