Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 562 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.1989. Min Range: -0.1989
Max Act: 0.1695. Min Act: -0.0001
Data Index: 1720361 (The Pile)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1989. Min Range: -0.1989
Max Act: 0.1886. Min Act: -0.0001
Data Index: 1121504 (The Pile)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1989. Min Range: -0.1989
Max Act: 0.1792. Min Act: -0.0001
Data Index: 1148972 (The Pile)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1989. Min Range: -0.1989
Max Act: 0.1711. Min Act: -0.0001
Data Index: 1927925 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1989. Min Range: -0.1989
Max Act: 0.1701. Min Act: -0.0001
Data Index: 996962 (The Pile)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1989. Min Range: -0.1989
Max Act: 0.1695. Min Act: -0.0001
Data Index: 341606 (The Pile)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1989. Min Range: -0.1989
Max Act: 0.1767. Min Act: -0.0001
Data Index: 550632 (The Pile)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1989. Min Range: -0.1989
Max Act: 0.1832. Min Act: -0.0001
Data Index: 435784 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1989. Min Range: -0.1989
Max Act: 0.1989. Min Act: -0.0001
Data Index: 1500573 (The Pile)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1989. Min Range: -0.1989
Max Act: 0.1713. Min Act: -0.0001
Data Index: 1198946 (The Pile)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1989. Min Range: -0.1989
Max Act: 0.1733. Min Act: -0.0001
Data Index: 140660 (The Pile)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1989. Min Range: -0.1989
Max Act: 0.1591. Min Act: -0.0002
Data Index: 814137 (The Pile)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1989. Min Range: -0.1989
Max Act: 0.1650. Min Act: -0.0001
Data Index: 967549 (The Pile)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1989. Min Range: -0.1989
Max Act: 0.1592. Min Act: -0.0001
Data Index: 1274082 (The Pile)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1989. Min Range: -0.1989
Max Act: 0.1629. Min Act: -0.0001
Data Index: 574997 (The Pile)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1989. Min Range: -0.1989
Max Act: 0.1751. Min Act: -0.0001
Data Index: 328755 (The Pile)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1989. Min Range: -0.1989
Max Act: 0.1572. Min Act: -0.0001
Data Index: 1762933 (The Pile)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1989. Min Range: -0.1989
Max Act: 0.1598. Min Act: -0.0001
Data Index: 1199770 (The Pile)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1989. Min Range: -0.1989
Max Act: 0.1464. Min Act: -0.0001
Data Index: 1448281 (The Pile)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1989. Min Range: -0.1989
Max Act: 0.1534. Min Act: -0.0002
Data Index: 357686 (The Pile)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #19