Model: None
Dataset: The Pile
Neuron 659 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 2.6119. Min Range: -2.6119
Max Act: 2.6119. Min Act: -0.1700
Data Index: 1677221 (The Pile)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6119. Min Range: -2.6119
Max Act: 2.5635. Min Act: -0.1700
Data Index: 1452755 (The Pile)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6119. Min Range: -2.6119
Max Act: 2.4989. Min Act: -0.1700
Data Index: 6215759 (The Pile)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6119. Min Range: -2.6119
Max Act: 2.4665. Min Act: -0.1700
Data Index: 10776867 (The Pile)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6119. Min Range: -2.6119
Max Act: 2.4827. Min Act: -0.1700
Data Index: 6935717 (The Pile)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6119. Min Range: -2.6119
Max Act: 2.4340. Min Act: -0.1700
Data Index: 5554011 (The Pile)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6119. Min Range: -2.6119
Max Act: 2.4014. Min Act: -0.1700
Data Index: 6626930 (The Pile)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6119. Min Range: -2.6119
Max Act: 2.3851. Min Act: -0.1700
Data Index: 6191580 (The Pile)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6119. Min Range: -2.6119
Max Act: 2.3687. Min Act: -0.1700
Data Index: 860456 (The Pile)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6119. Min Range: -2.6119
Max Act: 2.3524. Min Act: -0.1699
Data Index: 1934140 (The Pile)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6119. Min Range: -2.6119
Max Act: 2.3851. Min Act: -0.1700
Data Index: 3432279 (The Pile)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6119. Min Range: -2.6119
Max Act: 2.3524. Min Act: -0.1700
Data Index: 9989770 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6119. Min Range: -2.6119
Max Act: 2.3524. Min Act: -0.1700
Data Index: 10480447 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6119. Min Range: -2.6119
Max Act: 2.3524. Min Act: -0.1700
Data Index: 7434728 (The Pile)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6119. Min Range: -2.6119
Max Act: 2.3360. Min Act: -0.1700
Data Index: 9902989 (The Pile)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6119. Min Range: -2.6119
Max Act: 2.3524. Min Act: -0.1700
Data Index: 5095761 (The Pile)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6119. Min Range: -2.6119
Max Act: 2.3360. Min Act: -0.1700
Data Index: 4606996 (The Pile)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6119. Min Range: -2.6119
Max Act: 2.3524. Min Act: -0.1700
Data Index: 6248979 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6119. Min Range: -2.6119
Max Act: 2.3196. Min Act: -0.1700
Data Index: 8635937 (The Pile)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6119. Min Range: -2.6119
Max Act: 2.3196. Min Act: -0.1700
Data Index: 2536569 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19