Model: None
Dataset: The Pile
Neuron 1901 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.3053. Min Range: -3.3053
Max Act: 3.3053. Min Act: -0.1700
Data Index: 9927829 (The Pile)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3053. Min Range: -3.3053
Max Act: 3.2739. Min Act: -0.1700
Data Index: 3516615 (The Pile)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3053. Min Range: -3.3053
Max Act: 3.2581. Min Act: -0.1700
Data Index: 8169782 (The Pile)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3053. Min Range: -3.3053
Max Act: 3.2267. Min Act: -0.1700
Data Index: 3645204 (The Pile)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3053. Min Range: -3.3053
Max Act: 3.2110. Min Act: -0.1700
Data Index: 9108593 (The Pile)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3053. Min Range: -3.3053
Max Act: 3.1952. Min Act: -0.1700
Data Index: 8670478 (The Pile)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3053. Min Range: -3.3053
Max Act: 3.1638. Min Act: -0.1700
Data Index: 7740241 (The Pile)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3053. Min Range: -3.3053
Max Act: 3.1480. Min Act: -0.1700
Data Index: 1792450 (The Pile)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3053. Min Range: -3.3053
Max Act: 3.1323. Min Act: -0.1700
Data Index: 418743 (The Pile)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3053. Min Range: -3.3053
Max Act: 3.1323. Min Act: -0.1700
Data Index: 2553034 (The Pile)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3053. Min Range: -3.3053
Max Act: 3.1165. Min Act: -0.1700
Data Index: 1609413 (The Pile)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3053. Min Range: -3.3053
Max Act: 3.1165. Min Act: -0.1700
Data Index: 1684115 (The Pile)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3053. Min Range: -3.3053
Max Act: 3.1165. Min Act: -0.1700
Data Index: 5691052 (The Pile)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3053. Min Range: -3.3053
Max Act: 3.1165. Min Act: -0.1700
Data Index: 9570789 (The Pile)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3053. Min Range: -3.3053
Max Act: 3.1165. Min Act: -0.1700
Data Index: 4427886 (The Pile)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3053. Min Range: -3.3053
Max Act: 3.1007. Min Act: -0.1700
Data Index: 3423573 (The Pile)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3053. Min Range: -3.3053
Max Act: 3.1007. Min Act: -0.1700
Data Index: 6695793 (The Pile)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3053. Min Range: -3.3053
Max Act: 3.1007. Min Act: -0.1700
Data Index: 8406576 (The Pile)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3053. Min Range: -3.3053
Max Act: 3.1007. Min Act: -0.1700
Data Index: 8968562 (The Pile)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3053. Min Range: -3.3053
Max Act: 3.1007. Min Act: -0.1700
Data Index: 1975 (The Pile)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #19