Model: None
Dataset: The Pile
Neuron 518 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 1.9423. Min Range: -1.9423
Max Act: 1.9423. Min Act: -0.1700
Data Index: 5876 (The Pile)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9423. Min Range: -1.9423
Max Act: 1.9423. Min Act: -0.1700
Data Index: 193869 (The Pile)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9423. Min Range: -1.9423
Max Act: 1.9423. Min Act: -0.1700
Data Index: 178069 (The Pile)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9423. Min Range: -1.9423
Max Act: 1.9423. Min Act: -0.1700
Data Index: 175781 (The Pile)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9423. Min Range: -1.9423
Max Act: 1.9423. Min Act: -0.1700
Data Index: 171970 (The Pile)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9423. Min Range: -1.9423
Max Act: 1.9423. Min Act: -0.1700
Data Index: 10560 (The Pile)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9423. Min Range: -1.9423
Max Act: 1.9423. Min Act: -0.1700
Data Index: 166252 (The Pile)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9423. Min Range: -1.9423
Max Act: 1.9423. Min Act: -0.1700
Data Index: 153645 (The Pile)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9423. Min Range: -1.9423
Max Act: 1.9423. Min Act: -0.1700
Data Index: 135681 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9423. Min Range: -1.9423
Max Act: 1.9423. Min Act: -0.1700
Data Index: 14148 (The Pile)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9423. Min Range: -1.9423
Max Act: 1.9423. Min Act: -0.1700
Data Index: 54731 (The Pile)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9423. Min Range: -1.9423
Max Act: 1.9423. Min Act: -0.1700
Data Index: 126069 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9423. Min Range: -1.9423
Max Act: 1.9423. Min Act: -0.1700
Data Index: 113000 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9423. Min Range: -1.9423
Max Act: 1.9423. Min Act: -0.1700
Data Index: 94893 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9423. Min Range: -1.9423
Max Act: 1.9423. Min Act: -0.1700
Data Index: 89164 (The Pile)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9423. Min Range: -1.9423
Max Act: 1.9423. Min Act: -0.1700
Data Index: 88010 (The Pile)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9423. Min Range: -1.9423
Max Act: 1.9423. Min Act: -0.1700
Data Index: 13876 (The Pile)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9423. Min Range: -1.9423
Max Act: 1.9423. Min Act: -0.1700
Data Index: 84927 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9423. Min Range: -1.9423
Max Act: 1.9423. Min Act: -0.1700
Data Index: 83940 (The Pile)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9423. Min Range: -1.9423
Max Act: 1.9423. Min Act: -0.1700
Data Index: 56915 (The Pile)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #19