Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 348 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.3921. Min Range: -1.3921

Max Act: 1.3921. Min Act: -0.0000

Data Index: 1570509 (The Pile)

Max Activating Token Index: 500

Text #1

Max Range: 1.3921. Min Range: -1.3921

Max Act: 1.2053. Min Act: -0.0000

Data Index: 609474 (The Pile)

Max Activating Token Index: 543

Text #2

Max Range: 1.3921. Min Range: -1.3921

Max Act: 1.0357. Min Act: -0.0000

Data Index: 820911 (The Pile)

Max Activating Token Index: 860

Text #3

Max Range: 1.3921. Min Range: -1.3921

Max Act: 1.1265. Min Act: -0.0000

Data Index: 1508838 (The Pile)

Max Activating Token Index: 278

Text #4

Max Range: 1.3921. Min Range: -1.3921

Max Act: 1.0504. Min Act: -0.0000

Data Index: 224902 (The Pile)

Max Activating Token Index: 495

Text #5

Max Range: 1.3921. Min Range: -1.3921

Max Act: 1.0631. Min Act: -0.0000

Data Index: 1403013 (The Pile)

Max Activating Token Index: 232

Text #6

Max Range: 1.3921. Min Range: -1.3921

Max Act: 1.1549. Min Act: -0.0000

Data Index: 1189939 (The Pile)

Max Activating Token Index: 937

Text #7

Max Range: 1.3921. Min Range: -1.3921

Max Act: 1.0950. Min Act: -0.0000

Data Index: 1211343 (The Pile)

Max Activating Token Index: 845

Text #8

Max Range: 1.3921. Min Range: -1.3921

Max Act: 0.9930. Min Act: -0.0000

Data Index: 1555460 (The Pile)

Max Activating Token Index: 170

Text #9

Max Range: 1.3921. Min Range: -1.3921

Max Act: 1.0491. Min Act: -0.0000

Data Index: 88551 (The Pile)

Max Activating Token Index: 855

Text #10

Max Range: 1.3921. Min Range: -1.3921

Max Act: 0.9824. Min Act: -0.0000

Data Index: 115934 (The Pile)

Max Activating Token Index: 410

Text #11

Max Range: 1.3921. Min Range: -1.3921

Max Act: 1.0111. Min Act: -0.0000

Data Index: 369922 (The Pile)

Max Activating Token Index: 544

Text #12

Max Range: 1.3921. Min Range: -1.3921

Max Act: 0.9896. Min Act: -0.0000

Data Index: 545896 (The Pile)

Max Activating Token Index: 882

Text #13

Max Range: 1.3921. Min Range: -1.3921

Max Act: 0.9629. Min Act: -0.0000

Data Index: 796563 (The Pile)

Max Activating Token Index: 89

Text #14

Max Range: 1.3921. Min Range: -1.3921

Max Act: 0.9271. Min Act: -0.0000

Data Index: 1055236 (The Pile)

Max Activating Token Index: 875

Text #15

Max Range: 1.3921. Min Range: -1.3921

Max Act: 1.0088. Min Act: -0.0000

Data Index: 188109 (The Pile)

Max Activating Token Index: 550

Text #16

Max Range: 1.3921. Min Range: -1.3921

Max Act: 0.8689. Min Act: -0.0000

Data Index: 726710 (The Pile)

Max Activating Token Index: 574

Text #17

Max Range: 1.3921. Min Range: -1.3921

Max Act: 0.9447. Min Act: -0.0000

Data Index: 213894 (The Pile)

Max Activating Token Index: 413

Text #18

Max Range: 1.3921. Min Range: -1.3921

Max Act: 0.9425. Min Act: -0.0000

Data Index: 1010657 (The Pile)

Max Activating Token Index: 544

Text #19

Max Range: 1.3921. Min Range: -1.3921

Max Act: 0.9361. Min Act: -0.0000

Data Index: 1911371 (The Pile)

Max Activating Token Index: 146