Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1797 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4009. Min Range: -5.4009
Max Act: 5.4009. Min Act: -0.1700
Data Index: 1469935 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4009. Min Range: -5.4009
Max Act: 5.3697. Min Act: -0.1700
Data Index: 5511974 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4009. Min Range: -5.4009
Max Act: 5.3697. Min Act: -0.1700
Data Index: 1546013 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4009. Min Range: -5.4009
Max Act: 5.2134. Min Act: -0.1700
Data Index: 3045068 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4009. Min Range: -5.4009
Max Act: 5.1197. Min Act: -0.1700
Data Index: 8474048 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4009. Min Range: -5.4009
Max Act: 5.1197. Min Act: -0.1700
Data Index: 6816789 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4009. Min Range: -5.4009
Max Act: 5.1197. Min Act: -0.1700
Data Index: 7998176 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4009. Min Range: -5.4009
Max Act: 5.1197. Min Act: -0.1700
Data Index: 6628755 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4009. Min Range: -5.4009
Max Act: 5.1197. Min Act: -0.1700
Data Index: 1563610 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4009. Min Range: -5.4009
Max Act: 5.1197. Min Act: -0.1700
Data Index: 1575349 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4009. Min Range: -5.4009
Max Act: 5.0884. Min Act: -0.1700
Data Index: 2115685 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4009. Min Range: -5.4009
Max Act: 5.0884. Min Act: -0.1700
Data Index: 2676989 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4009. Min Range: -5.4009
Max Act: 5.0884. Min Act: -0.1700
Data Index: 6373656 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4009. Min Range: -5.4009
Max Act: 5.0884. Min Act: -0.1700
Data Index: 7760084 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4009. Min Range: -5.4009
Max Act: 5.0572. Min Act: -0.1700
Data Index: 898543 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4009. Min Range: -5.4009
Max Act: 5.0572. Min Act: -0.1700
Data Index: 5564667 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4009. Min Range: -5.4009
Max Act: 5.0259. Min Act: -0.1700
Data Index: 2764931 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4009. Min Range: -5.4009
Max Act: 5.0572. Min Act: -0.1700
Data Index: 4586257 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4009. Min Range: -5.4009
Max Act: 5.0259. Min Act: -0.1700
Data Index: 4287708 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4009. Min Range: -5.4009
Max Act: 5.0259. Min Act: -0.1700
Data Index: 5111666 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #19