Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4101 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9081. Min Range: -6.9081
Max Act: 6.9081. Min Act: -0.1700
Data Index: 598589 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9081. Min Range: -6.9081
Max Act: 6.8144. Min Act: -0.1700
Data Index: 2172262 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9081. Min Range: -6.9081
Max Act: 6.8144. Min Act: -0.1700
Data Index: 2027640 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9081. Min Range: -6.9081
Max Act: 6.8144. Min Act: -0.1700
Data Index: 7134798 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9081. Min Range: -6.9081
Max Act: 6.8456. Min Act: -0.1700
Data Index: 5602462 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9081. Min Range: -6.9081
Max Act: 6.7519. Min Act: -0.1700
Data Index: 7022347 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9081. Min Range: -6.9081
Max Act: 6.7519. Min Act: -0.1700
Data Index: 8543846 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9081. Min Range: -6.9081
Max Act: 6.6894. Min Act: -0.1699
Data Index: 5642105 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9081. Min Range: -6.9081
Max Act: 6.6894. Min Act: -0.1700
Data Index: 4866802 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9081. Min Range: -6.9081
Max Act: 6.6894. Min Act: -0.1700
Data Index: 2585033 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9081. Min Range: -6.9081
Max Act: 6.7206. Min Act: -0.1700
Data Index: 649124 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9081. Min Range: -6.9081
Max Act: 6.6581. Min Act: -0.1700
Data Index: 5079475 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9081. Min Range: -6.9081
Max Act: 6.6581. Min Act: -0.1700
Data Index: 7684301 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9081. Min Range: -6.9081
Max Act: 6.6581. Min Act: -0.1700
Data Index: 5209622 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9081. Min Range: -6.9081
Max Act: 6.6581. Min Act: -0.1700
Data Index: 2497529 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9081. Min Range: -6.9081
Max Act: 6.5956. Min Act: -0.1700
Data Index: 8778002 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9081. Min Range: -6.9081
Max Act: 6.6269. Min Act: -0.1700
Data Index: 3202623 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9081. Min Range: -6.9081
Max Act: 6.6269. Min Act: -0.1700
Data Index: 985126 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9081. Min Range: -6.9081
Max Act: 6.6269. Min Act: -0.1700
Data Index: 7424180 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9081. Min Range: -6.9081
Max Act: 6.5956. Min Act: -0.1700
Data Index: 3880324 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #19