Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3156 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7490. Min Range: -7.7490
Max Act: 7.7490. Min Act: -0.1700
Data Index: 710874 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7490. Min Range: -7.7490
Max Act: 7.6865. Min Act: -0.1700
Data Index: 2699461 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7490. Min Range: -7.7490
Max Act: 7.6240. Min Act: -0.1700
Data Index: 8132211 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7490. Min Range: -7.7490
Max Act: 7.5615. Min Act: -0.1700
Data Index: 171443 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7490. Min Range: -7.7490
Max Act: 7.5615. Min Act: -0.1700
Data Index: 3240140 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7490. Min Range: -7.7490
Max Act: 7.5615. Min Act: -0.1700
Data Index: 7884378 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7490. Min Range: -7.7490
Max Act: 7.4990. Min Act: -0.1700
Data Index: 4924236 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7490. Min Range: -7.7490
Max Act: 7.4990. Min Act: -0.1700
Data Index: 112712 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7490. Min Range: -7.7490
Max Act: 7.4677. Min Act: -0.1700
Data Index: 3292008 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7490. Min Range: -7.7490
Max Act: 7.4677. Min Act: -0.1700
Data Index: 3337507 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7490. Min Range: -7.7490
Max Act: 7.4677. Min Act: -0.1700
Data Index: 3741666 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7490. Min Range: -7.7490
Max Act: 7.4365. Min Act: -0.1700
Data Index: 6711013 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7490. Min Range: -7.7490
Max Act: 7.4052. Min Act: -0.1700
Data Index: 3771001 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7490. Min Range: -7.7490
Max Act: 7.4365. Min Act: -0.1700
Data Index: 3335274 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7490. Min Range: -7.7490
Max Act: 7.4052. Min Act: -0.1700
Data Index: 4792977 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7490. Min Range: -7.7490
Max Act: 7.4052. Min Act: -0.1700
Data Index: 6766673 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7490. Min Range: -7.7490
Max Act: 7.4365. Min Act: -0.1700
Data Index: 4890442 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7490. Min Range: -7.7490
Max Act: 7.4052. Min Act: -0.1700
Data Index: 1874019 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7490. Min Range: -7.7490
Max Act: 7.3427. Min Act: -0.1700
Data Index: 7127188 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7490. Min Range: -7.7490
Max Act: 7.3115. Min Act: -0.1700
Data Index: 1865550 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #19