Model: None
Dataset: The Pile
Neuron 1018 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 4.5411. Min Range: -4.5411
Max Act: 4.4474. Min Act: -0.1699
Data Index: 7291446 (The Pile)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5411. Min Range: -4.5411
Max Act: 4.5099. Min Act: -0.1699
Data Index: 3339681 (The Pile)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5411. Min Range: -4.5411
Max Act: 4.1973. Min Act: -0.1700
Data Index: 3601391 (The Pile)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5411. Min Range: -4.5411
Max Act: 4.3849. Min Act: -0.1700
Data Index: 3015998 (The Pile)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5411. Min Range: -4.5411
Max Act: 4.0410. Min Act: -0.1700
Data Index: 4305434 (The Pile)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5411. Min Range: -4.5411
Max Act: 4.4474. Min Act: -0.1700
Data Index: 9290939 (The Pile)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5411. Min Range: -4.5411
Max Act: 4.5099. Min Act: -0.1700
Data Index: 3534700 (The Pile)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5411. Min Range: -4.5411
Max Act: 4.0098. Min Act: -0.1700
Data Index: 88367 (The Pile)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5411. Min Range: -4.5411
Max Act: 3.7909. Min Act: -0.1700
Data Index: 3541135 (The Pile)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5411. Min Range: -4.5411
Max Act: 3.7283. Min Act: -0.1700
Data Index: 8109036 (The Pile)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5411. Min Range: -4.5411
Max Act: 3.8534. Min Act: -0.1700
Data Index: 5028826 (The Pile)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5411. Min Range: -4.5411
Max Act: 4.0723. Min Act: -0.1700
Data Index: 5384015 (The Pile)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5411. Min Range: -4.5411
Max Act: 4.2598. Min Act: -0.1700
Data Index: 7760780 (The Pile)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5411. Min Range: -4.5411
Max Act: 4.0410. Min Act: -0.1700
Data Index: 1975316 (The Pile)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5411. Min Range: -4.5411
Max Act: 4.1036. Min Act: -0.1700
Data Index: 3536228 (The Pile)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5411. Min Range: -4.5411
Max Act: 3.9785. Min Act: -0.1699
Data Index: 2610853 (The Pile)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5411. Min Range: -4.5411
Max Act: 4.0410. Min Act: -0.1700
Data Index: 8746400 (The Pile)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5411. Min Range: -4.5411
Max Act: 4.5411. Min Act: -0.1700
Data Index: 3049188 (The Pile)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5411. Min Range: -4.5411
Max Act: 3.7283. Min Act: -0.1700
Data Index: 2870451 (The Pile)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5411. Min Range: -4.5411
Max Act: 4.0410. Min Act: -0.1700
Data Index: 686061 (The Pile)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #19