Model: None
Dataset: The Pile
Neuron 4031 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.2124. Min Range: -3.2124
Max Act: 3.2124. Min Act: -0.1700
Data Index: 7441456 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2124. Min Range: -3.2124
Max Act: 3.1967. Min Act: -0.1700
Data Index: 3139986 (The Pile)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2124. Min Range: -3.2124
Max Act: 3.1495. Min Act: -0.1700
Data Index: 2301083 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2124. Min Range: -3.2124
Max Act: 3.1180. Min Act: -0.1700
Data Index: 4227308 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2124. Min Range: -3.2124
Max Act: 3.0707. Min Act: -0.1700
Data Index: 9347075 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2124. Min Range: -3.2124
Max Act: 3.0549. Min Act: -0.1700
Data Index: 3901012 (The Pile)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2124. Min Range: -3.2124
Max Act: 3.0233. Min Act: -0.1700
Data Index: 209169 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2124. Min Range: -3.2124
Max Act: 3.0075. Min Act: -0.1700
Data Index: 10647048 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2124. Min Range: -3.2124
Max Act: 3.0075. Min Act: -0.1700
Data Index: 306371 (The Pile)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2124. Min Range: -3.2124
Max Act: 3.0075. Min Act: -0.1699
Data Index: 9581730 (The Pile)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2124. Min Range: -3.2124
Max Act: 3.0075. Min Act: -0.1700
Data Index: 10043565 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2124. Min Range: -3.2124
Max Act: 2.9917. Min Act: -0.1700
Data Index: 4227101 (The Pile)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2124. Min Range: -3.2124
Max Act: 2.9917. Min Act: -0.1700
Data Index: 8151584 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2124. Min Range: -3.2124
Max Act: 2.9917. Min Act: -0.1700
Data Index: 5696759 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2124. Min Range: -3.2124
Max Act: 2.9917. Min Act: -0.1700
Data Index: 7133977 (The Pile)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2124. Min Range: -3.2124
Max Act: 2.9917. Min Act: -0.1700
Data Index: 3352410 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2124. Min Range: -3.2124
Max Act: 2.9759. Min Act: -0.1700
Data Index: 646862 (The Pile)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2124. Min Range: -3.2124
Max Act: 2.9759. Min Act: -0.1700
Data Index: 4497352 (The Pile)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2124. Min Range: -3.2124
Max Act: 2.9759. Min Act: -0.1700
Data Index: 113104 (The Pile)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2124. Min Range: -3.2124
Max Act: 2.9759. Min Act: -0.1700
Data Index: 9601144 (The Pile)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #19