Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3503 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0696. Min Range: -7.0696
Max Act: 7.0696. Min Act: -0.1700
Data Index: 6314588 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0696. Min Range: -7.0696
Max Act: 6.9759. Min Act: -0.1700
Data Index: 7861198 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0696. Min Range: -7.0696
Max Act: 6.9759. Min Act: -0.1700
Data Index: 6986139 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0696. Min Range: -7.0696
Max Act: 6.9446. Min Act: -0.1700
Data Index: 1411809 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0696. Min Range: -7.0696
Max Act: 6.7884. Min Act: -0.1700
Data Index: 7729147 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0696. Min Range: -7.0696
Max Act: 6.7884. Min Act: -0.1700
Data Index: 1249006 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0696. Min Range: -7.0696
Max Act: 6.6321. Min Act: -0.1700
Data Index: 8106615 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0696. Min Range: -7.0696
Max Act: 6.6634. Min Act: -0.1700
Data Index: 1575970 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0696. Min Range: -7.0696
Max Act: 6.6634. Min Act: -0.1700
Data Index: 5945253 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0696. Min Range: -7.0696
Max Act: 6.6634. Min Act: -0.1700
Data Index: 659004 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0696. Min Range: -7.0696
Max Act: 6.6634. Min Act: -0.1700
Data Index: 2766989 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0696. Min Range: -7.0696
Max Act: 6.6321. Min Act: -0.1700
Data Index: 394518 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0696. Min Range: -7.0696
Max Act: 6.6321. Min Act: -0.1700
Data Index: 1172479 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0696. Min Range: -7.0696
Max Act: 6.6009. Min Act: -0.1700
Data Index: 3146282 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0696. Min Range: -7.0696
Max Act: 6.5696. Min Act: -0.1700
Data Index: 1525860 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0696. Min Range: -7.0696
Max Act: 6.5384. Min Act: -0.1700
Data Index: 2858437 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0696. Min Range: -7.0696
Max Act: 6.5071. Min Act: -0.1700
Data Index: 1353107 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0696. Min Range: -7.0696
Max Act: 6.5071. Min Act: -0.1700
Data Index: 1172478 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0696. Min Range: -7.0696
Max Act: 6.4759. Min Act: -0.1700
Data Index: 3472361 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0696. Min Range: -7.0696
Max Act: 6.4759. Min Act: -0.1700
Data Index: 5087529 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #19