Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3157 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1716. Min Range: -10.1716
Max Act: 10.1716. Min Act: -0.1700
Data Index: 8555817 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1716. Min Range: -10.1716
Max Act: 10.1091. Min Act: -0.1700
Data Index: 2395582 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1716. Min Range: -10.1716
Max Act: 9.9841. Min Act: -0.1700
Data Index: 3598075 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1716. Min Range: -10.1716
Max Act: 9.9841. Min Act: -0.1700
Data Index: 4575986 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1716. Min Range: -10.1716
Max Act: 9.7966. Min Act: -0.1700
Data Index: 1119879 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1716. Min Range: -10.1716
Max Act: 9.6091. Min Act: -0.1700
Data Index: 3970155 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1716. Min Range: -10.1716
Max Act: 9.5466. Min Act: -0.1700
Data Index: 7359932 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1716. Min Range: -10.1716
Max Act: 9.5466. Min Act: -0.1700
Data Index: 8499029 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1716. Min Range: -10.1716
Max Act: 9.5466. Min Act: -0.1700
Data Index: 1498960 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1716. Min Range: -10.1716
Max Act: 9.5466. Min Act: -0.1700
Data Index: 2951614 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1716. Min Range: -10.1716
Max Act: 9.4216. Min Act: -0.1700
Data Index: 3219444 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1716. Min Range: -10.1716
Max Act: 9.4841. Min Act: -0.1700
Data Index: 7000230 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1716. Min Range: -10.1716
Max Act: 9.4841. Min Act: -0.1700
Data Index: 4031147 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1716. Min Range: -10.1716
Max Act: 9.4841. Min Act: -0.1700
Data Index: 2339670 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1716. Min Range: -10.1716
Max Act: 9.4841. Min Act: -0.1700
Data Index: 8698538 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1716. Min Range: -10.1716
Max Act: 9.4216. Min Act: -0.1700
Data Index: 2789573 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1716. Min Range: -10.1716
Max Act: 9.4216. Min Act: -0.1700
Data Index: 1762749 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1716. Min Range: -10.1716
Max Act: 9.4216. Min Act: -0.1700
Data Index: 849838 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1716. Min Range: -10.1716
Max Act: 9.4216. Min Act: -0.1700
Data Index: 6600192 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1716. Min Range: -10.1716
Max Act: 9.3591. Min Act: -0.1700
Data Index: 1763268 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #19