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

Dataset: The Pile

Neuron 3947 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2726. Min Range: -3.2726

Max Act: 3.2726. Min Act: -0.0000

Data Index: 435294 (The Pile)

Max Activating Token Index: 702

Text #1

Max Range: 3.2726. Min Range: -3.2726

Max Act: 3.0710. Min Act: -0.0000

Data Index: 727936 (The Pile)

Max Activating Token Index: 729

Text #2

Max Range: 3.2726. Min Range: -3.2726

Max Act: 3.0209. Min Act: -0.0000

Data Index: 1332977 (The Pile)

Max Activating Token Index: 564

Text #3

Max Range: 3.2726. Min Range: -3.2726

Max Act: 3.0151. Min Act: -0.0000

Data Index: 796321 (The Pile)

Max Activating Token Index: 748

Text #4

Max Range: 3.2726. Min Range: -3.2726

Max Act: 2.9738. Min Act: -0.0000

Data Index: 1882363 (The Pile)

Max Activating Token Index: 466

Text #5

Max Range: 3.2726. Min Range: -3.2726

Max Act: 3.0681. Min Act: -0.0000

Data Index: 1699107 (The Pile)

Max Activating Token Index: 351

Text #6

Max Range: 3.2726. Min Range: -3.2726

Max Act: 2.7160. Min Act: -0.0000

Data Index: 1453022 (The Pile)

Max Activating Token Index: 882

Text #7

Max Range: 3.2726. Min Range: -3.2726

Max Act: 2.8268. Min Act: -0.0000

Data Index: 1083823 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 3.2726. Min Range: -3.2726

Max Act: 2.5983. Min Act: -0.0000

Data Index: 1029556 (The Pile)

Max Activating Token Index: 269

Text #9

Max Range: 3.2726. Min Range: -3.2726

Max Act: 2.6985. Min Act: -0.0000

Data Index: 225707 (The Pile)

Max Activating Token Index: 682

Text #10

Max Range: 3.2726. Min Range: -3.2726

Max Act: 2.6388. Min Act: -0.0000

Data Index: 341693 (The Pile)

Max Activating Token Index: 747

Text #11

Max Range: 3.2726. Min Range: -3.2726

Max Act: 2.6211. Min Act: -0.0000

Data Index: 1793473 (The Pile)

Max Activating Token Index: 118

Text #12

Max Range: 3.2726. Min Range: -3.2726

Max Act: 2.6247. Min Act: -0.0000

Data Index: 669781 (The Pile)

Max Activating Token Index: 213

Text #13

Max Range: 3.2726. Min Range: -3.2726

Max Act: 2.6227. Min Act: -0.0000

Data Index: 1742606 (The Pile)

Max Activating Token Index: 578

Text #14

Max Range: 3.2726. Min Range: -3.2726

Max Act: 2.4664. Min Act: -0.0000

Data Index: 618142 (The Pile)

Max Activating Token Index: 602

Text #15

Max Range: 3.2726. Min Range: -3.2726

Max Act: 2.6368. Min Act: -0.0000

Data Index: 49092 (The Pile)

Max Activating Token Index: 187

Text #16

Max Range: 3.2726. Min Range: -3.2726

Max Act: 2.6088. Min Act: -0.0000

Data Index: 1621393 (The Pile)

Max Activating Token Index: 41

Text #17

Max Range: 3.2726. Min Range: -3.2726

Max Act: 2.3964. Min Act: -0.0000

Data Index: 159473 (The Pile)

Max Activating Token Index: 728

Text #18

Max Range: 3.2726. Min Range: -3.2726

Max Act: 2.5604. Min Act: -0.0000

Data Index: 1598508 (The Pile)

Max Activating Token Index: 493

Text #19

Max Range: 3.2726. Min Range: -3.2726

Max Act: 2.5615. Min Act: -0.0000

Data Index: 1839415 (The Pile)

Max Activating Token Index: 315