Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2734 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4785. Min Range: -5.4785
Max Act: 5.4785. Min Act: -0.1700
Data Index: 2311307 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4785. Min Range: -5.4785
Max Act: 5.2597. Min Act: -0.1700
Data Index: 8576162 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4785. Min Range: -5.4785
Max Act: 5.1347. Min Act: -0.1700
Data Index: 6381453 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4785. Min Range: -5.4785
Max Act: 5.1035. Min Act: -0.1700
Data Index: 6142050 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4785. Min Range: -5.4785
Max Act: 4.9785. Min Act: -0.1700
Data Index: 5692237 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4785. Min Range: -5.4785
Max Act: 5.0097. Min Act: -0.1700
Data Index: 8597750 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4785. Min Range: -5.4785
Max Act: 5.0097. Min Act: -0.1700
Data Index: 6419459 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4785. Min Range: -5.4785
Max Act: 4.9472. Min Act: -0.1700
Data Index: 855341 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4785. Min Range: -5.4785
Max Act: 4.9472. Min Act: -0.1700
Data Index: 8727589 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4785. Min Range: -5.4785
Max Act: 4.9160. Min Act: -0.1700
Data Index: 5209564 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4785. Min Range: -5.4785
Max Act: 4.9160. Min Act: -0.1700
Data Index: 5209568 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4785. Min Range: -5.4785
Max Act: 4.9160. Min Act: -0.1700
Data Index: 2887022 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4785. Min Range: -5.4785
Max Act: 4.9160. Min Act: -0.1700
Data Index: 8344630 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4785. Min Range: -5.4785
Max Act: 4.8535. Min Act: -0.1700
Data Index: 3175901 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4785. Min Range: -5.4785
Max Act: 4.8847. Min Act: -0.1700
Data Index: 2551530 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4785. Min Range: -5.4785
Max Act: 4.8535. Min Act: -0.1700
Data Index: 2656718 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4785. Min Range: -5.4785
Max Act: 4.8535. Min Act: -0.1700
Data Index: 2549218 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4785. Min Range: -5.4785
Max Act: 4.8535. Min Act: -0.1700
Data Index: 4355710 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4785. Min Range: -5.4785
Max Act: 4.8535. Min Act: -0.1700
Data Index: 858122 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4785. Min Range: -5.4785
Max Act: 4.8222. Min Act: -0.1700
Data Index: 854030 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #19