Model: None
Dataset: The Pile
Neuron 2097 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.3964. Min Range: -3.3964
Max Act: 3.3964. Min Act: -0.1700
Data Index: 5697213 (The Pile)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3964. Min Range: -3.3964
Max Act: 3.3493. Min Act: -0.1700
Data Index: 9757734 (The Pile)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3964. Min Range: -3.3964
Max Act: 3.3493. Min Act: -0.1700
Data Index: 3829865 (The Pile)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3964. Min Range: -3.3964
Max Act: 3.2865. Min Act: -0.1700
Data Index: 8043079 (The Pile)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3964. Min Range: -3.3964
Max Act: 3.2865. Min Act: -0.1700
Data Index: 1442349 (The Pile)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3964. Min Range: -3.3964
Max Act: 3.2394. Min Act: -0.1700
Data Index: 9678411 (The Pile)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3964. Min Range: -3.3964
Max Act: 3.2236. Min Act: -0.1700
Data Index: 3721662 (The Pile)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3964. Min Range: -3.3964
Max Act: 3.2079. Min Act: -0.1700
Data Index: 7763229 (The Pile)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3964. Min Range: -3.3964
Max Act: 3.1922. Min Act: -0.1700
Data Index: 4776041 (The Pile)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3964. Min Range: -3.3964
Max Act: 3.1764. Min Act: -0.1700
Data Index: 8427834 (The Pile)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3964. Min Range: -3.3964
Max Act: 3.1764. Min Act: -0.1700
Data Index: 5447224 (The Pile)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3964. Min Range: -3.3964
Max Act: 3.1764. Min Act: -0.1700
Data Index: 9269585 (The Pile)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3964. Min Range: -3.3964
Max Act: 3.1607. Min Act: -0.1700
Data Index: 320928 (The Pile)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3964. Min Range: -3.3964
Max Act: 3.1607. Min Act: -0.1700
Data Index: 3974600 (The Pile)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3964. Min Range: -3.3964
Max Act: 3.1449. Min Act: -0.1700
Data Index: 8276334 (The Pile)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3964. Min Range: -3.3964
Max Act: 3.1449. Min Act: -0.1700
Data Index: 10595178 (The Pile)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3964. Min Range: -3.3964
Max Act: 3.1449. Min Act: -0.1700
Data Index: 6134781 (The Pile)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3964. Min Range: -3.3964
Max Act: 3.1449. Min Act: -0.1700
Data Index: 5204669 (The Pile)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3964. Min Range: -3.3964
Max Act: 3.1449. Min Act: -0.1700
Data Index: 2282422 (The Pile)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3964. Min Range: -3.3964
Max Act: 3.1292. Min Act: -0.1700
Data Index: 5421947 (The Pile)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #19