Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3370 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7188. Min Range: -5.7188
Max Act: 5.7188. Min Act: -0.1700
Data Index: 5201706 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7188. Min Range: -5.7188
Max Act: 5.6563. Min Act: -0.1700
Data Index: 3023803 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7188. Min Range: -5.7188
Max Act: 5.5626. Min Act: -0.1700
Data Index: 6360912 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7188. Min Range: -5.7188
Max Act: 5.4376. Min Act: -0.1700
Data Index: 2099734 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7188. Min Range: -5.7188
Max Act: 5.2813. Min Act: -0.1700
Data Index: 5815293 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7188. Min Range: -5.7188
Max Act: 5.2188. Min Act: -0.1700
Data Index: 7508816 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7188. Min Range: -5.7188
Max Act: 5.2188. Min Act: -0.1700
Data Index: 4912768 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7188. Min Range: -5.7188
Max Act: 5.1876. Min Act: -0.1700
Data Index: 1012316 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7188. Min Range: -5.7188
Max Act: 5.1251. Min Act: -0.1700
Data Index: 6377209 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7188. Min Range: -5.7188
Max Act: 5.1563. Min Act: -0.1700
Data Index: 6268523 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7188. Min Range: -5.7188
Max Act: 5.1251. Min Act: -0.1700
Data Index: 6957989 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7188. Min Range: -5.7188
Max Act: 5.1251. Min Act: -0.1700
Data Index: 1542493 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7188. Min Range: -5.7188
Max Act: 5.1251. Min Act: -0.1700
Data Index: 7311104 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7188. Min Range: -5.7188
Max Act: 5.0938. Min Act: -0.1700
Data Index: 2198791 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7188. Min Range: -5.7188
Max Act: 5.0938. Min Act: -0.1700
Data Index: 8100038 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7188. Min Range: -5.7188
Max Act: 5.0938. Min Act: -0.1700
Data Index: 5226443 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7188. Min Range: -5.7188
Max Act: 5.0938. Min Act: -0.1700
Data Index: 63331 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7188. Min Range: -5.7188
Max Act: 5.0626. Min Act: -0.1700
Data Index: 220962 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7188. Min Range: -5.7188
Max Act: 5.0626. Min Act: -0.1700
Data Index: 7159824 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7188. Min Range: -5.7188
Max Act: 5.0626. Min Act: -0.1700
Data Index: 2407166 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #19