Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4423 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0085. Min Range: -3.0085
Max Act: 3.0085. Min Act: -0.1700
Data Index: 2241985 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0085. Min Range: -3.0085
Max Act: 2.9769. Min Act: -0.1700
Data Index: 1446442 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0085. Min Range: -3.0085
Max Act: 2.8819. Min Act: -0.1700
Data Index: 4288660 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0085. Min Range: -3.0085
Max Act: 2.8501. Min Act: -0.1700
Data Index: 6687365 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0085. Min Range: -3.0085
Max Act: 2.8501. Min Act: -0.1700
Data Index: 7503943 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0085. Min Range: -3.0085
Max Act: 2.8183. Min Act: -0.1700
Data Index: 3247365 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0085. Min Range: -3.0085
Max Act: 2.8024. Min Act: -0.1700
Data Index: 6823720 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0085. Min Range: -3.0085
Max Act: 2.8024. Min Act: -0.1700
Data Index: 937080 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0085. Min Range: -3.0085
Max Act: 2.7546. Min Act: -0.1700
Data Index: 290826 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0085. Min Range: -3.0085
Max Act: 2.7705. Min Act: -0.1700
Data Index: 8493503 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0085. Min Range: -3.0085
Max Act: 2.7705. Min Act: -0.1700
Data Index: 6804674 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0085. Min Range: -3.0085
Max Act: 2.7546. Min Act: -0.1700
Data Index: 7452484 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0085. Min Range: -3.0085
Max Act: 2.7546. Min Act: -0.1700
Data Index: 3945709 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0085. Min Range: -3.0085
Max Act: 2.7226. Min Act: -0.1700
Data Index: 7087109 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0085. Min Range: -3.0085
Max Act: 2.7066. Min Act: -0.1700
Data Index: 2878384 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0085. Min Range: -3.0085
Max Act: 2.7226. Min Act: -0.1700
Data Index: 3655628 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0085. Min Range: -3.0085
Max Act: 2.7226. Min Act: -0.1700
Data Index: 1663961 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0085. Min Range: -3.0085
Max Act: 2.7226. Min Act: -0.1700
Data Index: 6649792 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0085. Min Range: -3.0085
Max Act: 2.6906. Min Act: -0.1700
Data Index: 6855031 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0085. Min Range: -3.0085
Max Act: 2.7226. Min Act: -0.1700
Data Index: 5711986 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #19