Model: None
Dataset: The Pile
Neuron 1572 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-160m')
Text #0
Max Range: 2.8056. Min Range: -2.8056
Max Act: 2.8056. Min Act: -0.1700
Data Index: 725556 (The Pile)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8056. Min Range: -2.8056
Max Act: 2.7578. Min Act: -0.1700
Data Index: 4659659 (The Pile)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8056. Min Range: -2.8056
Max Act: 2.7578. Min Act: -0.1700
Data Index: 10529767 (The Pile)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8056. Min Range: -2.8056
Max Act: 2.7418. Min Act: -0.1700
Data Index: 6515377 (The Pile)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8056. Min Range: -2.8056
Max Act: 2.7418. Min Act: -0.1700
Data Index: 798585 (The Pile)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8056. Min Range: -2.8056
Max Act: 2.7418. Min Act: -0.1700
Data Index: 1852952 (The Pile)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8056. Min Range: -2.8056
Max Act: 2.7418. Min Act: -0.1700
Data Index: 7968023 (The Pile)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8056. Min Range: -2.8056
Max Act: 2.7258. Min Act: -0.1700
Data Index: 9329742 (The Pile)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8056. Min Range: -2.8056
Max Act: 2.7258. Min Act: -0.1700
Data Index: 7129415 (The Pile)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8056. Min Range: -2.8056
Max Act: 2.7258. Min Act: -0.1700
Data Index: 9593608 (The Pile)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8056. Min Range: -2.8056
Max Act: 2.7098. Min Act: -0.1700
Data Index: 4249193 (The Pile)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8056. Min Range: -2.8056
Max Act: 2.7098. Min Act: -0.1700
Data Index: 8771720 (The Pile)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8056. Min Range: -2.8056
Max Act: 2.7098. Min Act: -0.1700
Data Index: 653328 (The Pile)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8056. Min Range: -2.8056
Max Act: 2.7098. Min Act: -0.1700
Data Index: 10367611 (The Pile)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8056. Min Range: -2.8056
Max Act: 2.7098. Min Act: -0.1700
Data Index: 2242687 (The Pile)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8056. Min Range: -2.8056
Max Act: 2.7098. Min Act: -0.1700
Data Index: 10327003 (The Pile)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8056. Min Range: -2.8056
Max Act: 2.7098. Min Act: -0.1700
Data Index: 6810211 (The Pile)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8056. Min Range: -2.8056
Max Act: 2.6938. Min Act: -0.1700
Data Index: 8072830 (The Pile)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8056. Min Range: -2.8056
Max Act: 2.6938. Min Act: -0.1700
Data Index: 4390387 (The Pile)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8056. Min Range: -2.8056
Max Act: 2.6938. Min Act: -0.1700
Data Index: 8809791 (The Pile)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #19