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

Dataset: The Pile

Neuron 2724 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: 3.4475. Min Range: -3.4475

Max Act: 3.4475. Min Act: -0.0000

Data Index: 1329000 (The Pile)

Max Activating Token Index: 565

Text #1

Max Range: 3.4475. Min Range: -3.4475

Max Act: 3.0801. Min Act: -0.0000

Data Index: 715596 (The Pile)

Max Activating Token Index: 781

Text #2

Max Range: 3.4475. Min Range: -3.4475

Max Act: 2.9736. Min Act: -0.0000

Data Index: 1931934 (The Pile)

Max Activating Token Index: 414

Text #3

Max Range: 3.4475. Min Range: -3.4475

Max Act: 2.7143. Min Act: -0.0000

Data Index: 1771389 (The Pile)

Max Activating Token Index: 597

Text #4

Max Range: 3.4475. Min Range: -3.4475

Max Act: 2.8466. Min Act: -0.0000

Data Index: 34722 (The Pile)

Max Activating Token Index: 922

Text #5

Max Range: 3.4475. Min Range: -3.4475

Max Act: 2.9106. Min Act: -0.0000

Data Index: 1088395 (The Pile)

Max Activating Token Index: 80

Text #6

Max Range: 3.4475. Min Range: -3.4475

Max Act: 2.6405. Min Act: -0.0000

Data Index: 854758 (The Pile)

Max Activating Token Index: 458

Text #7

Max Range: 3.4475. Min Range: -3.4475

Max Act: 2.6719. Min Act: -0.0000

Data Index: 1348179 (The Pile)

Max Activating Token Index: 958

Text #8

Max Range: 3.4475. Min Range: -3.4475

Max Act: 2.4323. Min Act: -0.0000

Data Index: 249602 (The Pile)

Max Activating Token Index: 794

Text #9

Max Range: 3.4475. Min Range: -3.4475

Max Act: 2.5526. Min Act: -0.0000

Data Index: 253872 (The Pile)

Max Activating Token Index: 182

Text #10

Max Range: 3.4475. Min Range: -3.4475

Max Act: 2.6001. Min Act: -0.0000

Data Index: 1743246 (The Pile)

Max Activating Token Index: 724

Text #11

Max Range: 3.4475. Min Range: -3.4475

Max Act: 2.0438. Min Act: -0.0000

Data Index: 1100794 (The Pile)

Max Activating Token Index: 163

Text #12

Max Range: 3.4475. Min Range: -3.4475

Max Act: 2.1550. Min Act: -0.0000

Data Index: 1720010 (The Pile)

Max Activating Token Index: 268

Text #13

Max Range: 3.4475. Min Range: -3.4475

Max Act: 2.1338. Min Act: -0.0000

Data Index: 1233713 (The Pile)

Max Activating Token Index: 578

Text #14

Max Range: 3.4475. Min Range: -3.4475

Max Act: 2.1075. Min Act: -0.0000

Data Index: 131180 (The Pile)

Max Activating Token Index: 628

Text #15

Max Range: 3.4475. Min Range: -3.4475

Max Act: 2.2306. Min Act: -0.0000

Data Index: 629737 (The Pile)

Max Activating Token Index: 447

Text #16

Max Range: 3.4475. Min Range: -3.4475

Max Act: 1.9855. Min Act: -0.0000

Data Index: 1632902 (The Pile)

Max Activating Token Index: 25

Text #17

Max Range: 3.4475. Min Range: -3.4475

Max Act: 2.1898. Min Act: -0.0000

Data Index: 739276 (The Pile)

Max Activating Token Index: 458

Text #18

Max Range: 3.4475. Min Range: -3.4475

Max Act: 2.0825. Min Act: -0.0000

Data Index: 1303535 (The Pile)

Max Activating Token Index: 476

Text #19

Max Range: 3.4475. Min Range: -3.4475

Max Act: 2.0325. Min Act: -0.0000

Data Index: 551097 (The Pile)

Max Activating Token Index: 836