Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5965 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6179. Min Range: -8.6179
Max Act: 8.6179. Min Act: -0.1700
Data Index: 1024769 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6179. Min Range: -8.6179
Max Act: 7.8679. Min Act: -0.1700
Data Index: 3683626 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6179. Min Range: -8.6179
Max Act: 7.7429. Min Act: -0.1700
Data Index: 867222 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6179. Min Range: -8.6179
Max Act: 7.7429. Min Act: -0.1700
Data Index: 60787 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6179. Min Range: -8.6179
Max Act: 7.6804. Min Act: -0.1700
Data Index: 1679547 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6179. Min Range: -8.6179
Max Act: 7.6804. Min Act: -0.1700
Data Index: 7179863 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6179. Min Range: -8.6179
Max Act: 7.6179. Min Act: -0.1700
Data Index: 6766853 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6179. Min Range: -8.6179
Max Act: 7.4929. Min Act: -0.1700
Data Index: 5921699 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6179. Min Range: -8.6179
Max Act: 7.4929. Min Act: -0.1700
Data Index: 5194172 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6179. Min Range: -8.6179
Max Act: 7.4929. Min Act: -0.1700
Data Index: 7348206 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6179. Min Range: -8.6179
Max Act: 7.3991. Min Act: -0.1700
Data Index: 5816059 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6179. Min Range: -8.6179
Max Act: 7.4304. Min Act: -0.1700
Data Index: 5633522 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6179. Min Range: -8.6179
Max Act: 7.3679. Min Act: -0.1700
Data Index: 7738012 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6179. Min Range: -8.6179
Max Act: 7.3679. Min Act: -0.1700
Data Index: 432703 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6179. Min Range: -8.6179
Max Act: 7.3679. Min Act: -0.1700
Data Index: 7128514 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6179. Min Range: -8.6179
Max Act: 7.3991. Min Act: -0.1700
Data Index: 559988 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6179. Min Range: -8.6179
Max Act: 7.3366. Min Act: -0.1700
Data Index: 7547578 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6179. Min Range: -8.6179
Max Act: 7.3679. Min Act: -0.1700
Data Index: 3242985 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6179. Min Range: -8.6179
Max Act: 7.3366. Min Act: -0.1700
Data Index: 7724735 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6179. Min Range: -8.6179
Max Act: 7.3366. Min Act: -0.1700
Data Index: 2756393 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19