Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1223 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2848. Min Range: -5.2848
Max Act: 5.2848. Min Act: -0.1700
Data Index: 1618851 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2848. Min Range: -5.2848
Max Act: 5.1598. Min Act: -0.1700
Data Index: 8662535 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2848. Min Range: -5.2848
Max Act: 5.1598. Min Act: -0.1700
Data Index: 3684331 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2848. Min Range: -5.2848
Max Act: 5.0661. Min Act: -0.1700
Data Index: 686877 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2848. Min Range: -5.2848
Max Act: 5.0661. Min Act: -0.1700
Data Index: 4019264 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2848. Min Range: -5.2848
Max Act: 5.0036. Min Act: -0.1700
Data Index: 7507212 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2848. Min Range: -5.2848
Max Act: 4.9723. Min Act: -0.1700
Data Index: 579545 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2848. Min Range: -5.2848
Max Act: 4.9098. Min Act: -0.1700
Data Index: 2320868 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2848. Min Range: -5.2848
Max Act: 4.9098. Min Act: -0.1700
Data Index: 3235054 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2848. Min Range: -5.2848
Max Act: 4.9098. Min Act: -0.1700
Data Index: 634957 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2848. Min Range: -5.2848
Max Act: 4.8473. Min Act: -0.1700
Data Index: 5592788 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2848. Min Range: -5.2848
Max Act: 4.8473. Min Act: -0.1700
Data Index: 202891 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2848. Min Range: -5.2848
Max Act: 4.8473. Min Act: -0.1700
Data Index: 4963721 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2848. Min Range: -5.2848
Max Act: 4.8473. Min Act: -0.1700
Data Index: 7955071 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2848. Min Range: -5.2848
Max Act: 4.8786. Min Act: -0.1700
Data Index: 2921901 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2848. Min Range: -5.2848
Max Act: 4.8473. Min Act: -0.1700
Data Index: 3362010 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2848. Min Range: -5.2848
Max Act: 4.8161. Min Act: -0.1700
Data Index: 7568184 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2848. Min Range: -5.2848
Max Act: 4.8161. Min Act: -0.1700
Data Index: 6687187 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2848. Min Range: -5.2848
Max Act: 4.8161. Min Act: -0.1700
Data Index: 3235056 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2848. Min Range: -5.2848
Max Act: 4.8161. Min Act: -0.1700
Data Index: 686880 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #19