Model: None
Dataset: The Pile
Neuron 1069 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 3.2474. Min Range: -3.2474
Max Act: 3.2474. Min Act: -0.1700
Data Index: 1591844 (The Pile)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2474. Min Range: -3.2474
Max Act: 3.1688. Min Act: -0.1700
Data Index: 6946130 (The Pile)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2474. Min Range: -3.2474
Max Act: 3.1688. Min Act: -0.1700
Data Index: 2181348 (The Pile)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2474. Min Range: -3.2474
Max Act: 3.1530. Min Act: -0.1700
Data Index: 2570011 (The Pile)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2474. Min Range: -3.2474
Max Act: 3.1373. Min Act: -0.1700
Data Index: 7666698 (The Pile)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2474. Min Range: -3.2474
Max Act: 3.1530. Min Act: -0.1700
Data Index: 7313278 (The Pile)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2474. Min Range: -3.2474
Max Act: 3.1373. Min Act: -0.1700
Data Index: 7058408 (The Pile)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2474. Min Range: -3.2474
Max Act: 3.1215. Min Act: -0.1700
Data Index: 4542547 (The Pile)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2474. Min Range: -3.2474
Max Act: 3.1057. Min Act: -0.1700
Data Index: 10074238 (The Pile)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2474. Min Range: -3.2474
Max Act: 3.1057. Min Act: -0.1700
Data Index: 2424481 (The Pile)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2474. Min Range: -3.2474
Max Act: 3.1215. Min Act: -0.1700
Data Index: 1100887 (The Pile)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2474. Min Range: -3.2474
Max Act: 3.1057. Min Act: -0.1700
Data Index: 9233265 (The Pile)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2474. Min Range: -3.2474
Max Act: 3.1057. Min Act: -0.1700
Data Index: 861881 (The Pile)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2474. Min Range: -3.2474
Max Act: 3.1057. Min Act: -0.1700
Data Index: 1882233 (The Pile)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2474. Min Range: -3.2474
Max Act: 3.1215. Min Act: -0.1700
Data Index: 10423844 (The Pile)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2474. Min Range: -3.2474
Max Act: 3.1057. Min Act: -0.1700
Data Index: 10441977 (The Pile)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2474. Min Range: -3.2474
Max Act: 3.1057. Min Act: -0.1700
Data Index: 10023161 (The Pile)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2474. Min Range: -3.2474
Max Act: 3.1057. Min Act: -0.1700
Data Index: 8861662 (The Pile)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2474. Min Range: -3.2474
Max Act: 3.0900. Min Act: -0.1700
Data Index: 8904575 (The Pile)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2474. Min Range: -3.2474
Max Act: 3.0900. Min Act: -0.1700
Data Index: 5768909 (The Pile)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #19