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

Dataset: The Pile

Neuron 3914 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: 0.8880. Min Range: -0.8880

Max Act: 0.8880. Min Act: -0.0000

Data Index: 65981 (The Pile)

Max Activating Token Index: 691

Text #1

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.7712. Min Act: -0.0000

Data Index: 416495 (The Pile)

Max Activating Token Index: 713

Text #2

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.7191. Min Act: -0.0000

Data Index: 1274739 (The Pile)

Max Activating Token Index: 669

Text #3

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.6997. Min Act: -0.0000

Data Index: 429160 (The Pile)

Max Activating Token Index: 750

Text #4

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.6765. Min Act: -0.0000

Data Index: 325087 (The Pile)

Max Activating Token Index: 395

Text #5

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.7200. Min Act: -0.0000

Data Index: 808341 (The Pile)

Max Activating Token Index: 402

Text #6

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.6686. Min Act: -0.0000

Data Index: 1767986 (The Pile)

Max Activating Token Index: 862

Text #7

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.6224. Min Act: -0.0000

Data Index: 1032341 (The Pile)

Max Activating Token Index: 515

Text #8

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.5975. Min Act: -0.0000

Data Index: 964012 (The Pile)

Max Activating Token Index: 935

Text #9

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.6002. Min Act: -0.0000

Data Index: 994335 (The Pile)

Max Activating Token Index: 173

Text #10

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.6090. Min Act: -0.0000

Data Index: 23438 (The Pile)

Max Activating Token Index: 657

Text #11

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.6038. Min Act: -0.0000

Data Index: 321069 (The Pile)

Max Activating Token Index: 461

Text #12

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.6329. Min Act: -0.0000

Data Index: 1714991 (The Pile)

Max Activating Token Index: 979

Text #13

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.5986. Min Act: -0.0000

Data Index: 1238930 (The Pile)

Max Activating Token Index: 424

Text #14

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.5975. Min Act: -0.0000

Data Index: 1882013 (The Pile)

Max Activating Token Index: 522

Text #15

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.5992. Min Act: -0.0000

Data Index: 691678 (The Pile)

Max Activating Token Index: 813

Text #16

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.5998. Min Act: -0.0000

Data Index: 536829 (The Pile)

Max Activating Token Index: 814

Text #17

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.5847. Min Act: -0.0000

Data Index: 866042 (The Pile)

Max Activating Token Index: 621

Text #18

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.5647. Min Act: -0.0000

Data Index: 464992 (The Pile)

Max Activating Token Index: 1010

Text #19

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.5219. Min Act: -0.0000

Data Index: 929347 (The Pile)

Max Activating Token Index: 188