Model: None
Dataset: The Pile
Neuron 623 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 3.2925. Min Range: -3.2925
Max Act: 3.2925. Min Act: -0.1699
Data Index: 6719628 (The Pile)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2925. Min Range: -3.2925
Max Act: 3.2611. Min Act: -0.1700
Data Index: 10406410 (The Pile)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2925. Min Range: -3.2925
Max Act: 3.1509. Min Act: -0.1700
Data Index: 1820430 (The Pile)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2925. Min Range: -3.2925
Max Act: 3.1982. Min Act: -0.1698
Data Index: 8903625 (The Pile)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2925. Min Range: -3.2925
Max Act: 3.1194. Min Act: -0.1696
Data Index: 3328618 (The Pile)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2925. Min Range: -3.2925
Max Act: 3.0721. Min Act: -0.1700
Data Index: 496809 (The Pile)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2925. Min Range: -3.2925
Max Act: 3.0879. Min Act: -0.1696
Data Index: 2713249 (The Pile)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2925. Min Range: -3.2925
Max Act: 3.0405. Min Act: -0.1700
Data Index: 9375530 (The Pile)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2925. Min Range: -3.2925
Max Act: 3.0563. Min Act: -0.1700
Data Index: 3243129 (The Pile)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2925. Min Range: -3.2925
Max Act: 3.0721. Min Act: -0.1699
Data Index: 6927707 (The Pile)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2925. Min Range: -3.2925
Max Act: 3.0248. Min Act: -0.1700
Data Index: 1058853 (The Pile)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2925. Min Range: -3.2925
Max Act: 3.0248. Min Act: -0.1700
Data Index: 4858597 (The Pile)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2925. Min Range: -3.2925
Max Act: 3.0090. Min Act: -0.1696
Data Index: 3626920 (The Pile)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2925. Min Range: -3.2925
Max Act: 3.0090. Min Act: -0.1699
Data Index: 5462362 (The Pile)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2925. Min Range: -3.2925
Max Act: 3.0090. Min Act: -0.1696
Data Index: 30466 (The Pile)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2925. Min Range: -3.2925
Max Act: 3.0090. Min Act: -0.1700
Data Index: 7652476 (The Pile)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2925. Min Range: -3.2925
Max Act: 3.0090. Min Act: -0.1700
Data Index: 7254078 (The Pile)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2925. Min Range: -3.2925
Max Act: 3.0248. Min Act: -0.1698
Data Index: 8995918 (The Pile)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2925. Min Range: -3.2925
Max Act: 2.9931. Min Act: -0.1697
Data Index: 8402600 (The Pile)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2925. Min Range: -3.2925
Max Act: 2.9773. Min Act: -0.1700
Data Index: 1539244 (The Pile)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #19