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

Dataset: The Pile

Neuron 621 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2836. Min Range: -1.2836

Max Act: 1.2506. Min Act: -0.0000

Data Index: 354347 (The Pile)

Max Activating Token Index: 979

Text #1

Max Range: 1.2836. Min Range: -1.2836

Max Act: 1.2836. Min Act: -0.0000

Data Index: 1087444 (The Pile)

Max Activating Token Index: 741

Text #2

Max Range: 1.2836. Min Range: -1.2836

Max Act: 1.2220. Min Act: -0.0000

Data Index: 1427758 (The Pile)

Max Activating Token Index: 495

Text #3

Max Range: 1.2836. Min Range: -1.2836

Max Act: 1.1436. Min Act: -0.0000

Data Index: 1540981 (The Pile)

Max Activating Token Index: 915

Text #4

Max Range: 1.2836. Min Range: -1.2836

Max Act: 1.0709. Min Act: -0.0000

Data Index: 1744502 (The Pile)

Max Activating Token Index: 487

Text #5

Max Range: 1.2836. Min Range: -1.2836

Max Act: 1.0246. Min Act: -0.0000

Data Index: 124390 (The Pile)

Max Activating Token Index: 270

Text #6

Max Range: 1.2836. Min Range: -1.2836

Max Act: 1.0712. Min Act: -0.0000

Data Index: 182300 (The Pile)

Max Activating Token Index: 669

Text #7

Max Range: 1.2836. Min Range: -1.2836

Max Act: 0.9965. Min Act: -0.0000

Data Index: 1269868 (The Pile)

Max Activating Token Index: 702

Text #8

Max Range: 1.2836. Min Range: -1.2836

Max Act: 0.9678. Min Act: -0.0000

Data Index: 1247346 (The Pile)

Max Activating Token Index: 359

Text #9

Max Range: 1.2836. Min Range: -1.2836

Max Act: 0.9528. Min Act: -0.0001

Data Index: 1206452 (The Pile)

Max Activating Token Index: 902

Text #10

Max Range: 1.2836. Min Range: -1.2836

Max Act: 0.9050. Min Act: -0.0000

Data Index: 1143597 (The Pile)

Max Activating Token Index: 433

Text #11

Max Range: 1.2836. Min Range: -1.2836

Max Act: 0.9306. Min Act: -0.0000

Data Index: 1477914 (The Pile)

Max Activating Token Index: 557

Text #12

Max Range: 1.2836. Min Range: -1.2836

Max Act: 0.8558. Min Act: -0.0000

Data Index: 1767249 (The Pile)

Max Activating Token Index: 767

Text #13

Max Range: 1.2836. Min Range: -1.2836

Max Act: 0.9339. Min Act: -0.0000

Data Index: 1435219 (The Pile)

Max Activating Token Index: 521

Text #14

Max Range: 1.2836. Min Range: -1.2836

Max Act: 0.8837. Min Act: -0.0000

Data Index: 672547 (The Pile)

Max Activating Token Index: 732

Text #15

Max Range: 1.2836. Min Range: -1.2836

Max Act: 0.9001. Min Act: -0.0000

Data Index: 814109 (The Pile)

Max Activating Token Index: 249

Text #16

Max Range: 1.2836. Min Range: -1.2836

Max Act: 0.9481. Min Act: -0.0000

Data Index: 1392977 (The Pile)

Max Activating Token Index: 954

Text #17

Max Range: 1.2836. Min Range: -1.2836

Max Act: 0.8956. Min Act: -0.0000

Data Index: 983063 (The Pile)

Max Activating Token Index: 890

Text #18

Max Range: 1.2836. Min Range: -1.2836

Max Act: 0.9059. Min Act: -0.0000

Data Index: 669045 (The Pile)

Max Activating Token Index: 921

Text #19

Max Range: 1.2836. Min Range: -1.2836

Max Act: 0.8620. Min Act: -0.0000

Data Index: 1926619 (The Pile)

Max Activating Token Index: 167