Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5364 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0666. Min Range: -5.0666
Max Act: 5.0666. Min Act: -0.1700
Data Index: 2862595 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0666. Min Range: -5.0666
Max Act: 4.9729. Min Act: -0.1700
Data Index: 8762711 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0666. Min Range: -5.0666
Max Act: 4.9416. Min Act: -0.1700
Data Index: 441940 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0666. Min Range: -5.0666
Max Act: 4.9416. Min Act: -0.1700
Data Index: 1132679 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0666. Min Range: -5.0666
Max Act: 4.9104. Min Act: -0.1700
Data Index: 6544109 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0666. Min Range: -5.0666
Max Act: 4.9104. Min Act: -0.1700
Data Index: 4039232 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0666. Min Range: -5.0666
Max Act: 4.8791. Min Act: -0.1700
Data Index: 4494073 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0666. Min Range: -5.0666
Max Act: 4.8479. Min Act: -0.1700
Data Index: 4263203 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0666. Min Range: -5.0666
Max Act: 4.8791. Min Act: -0.1700
Data Index: 6367318 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0666. Min Range: -5.0666
Max Act: 4.8479. Min Act: -0.1700
Data Index: 3851879 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0666. Min Range: -5.0666
Max Act: 4.8479. Min Act: -0.1700
Data Index: 6976963 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0666. Min Range: -5.0666
Max Act: 4.8479. Min Act: -0.1700
Data Index: 8494586 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0666. Min Range: -5.0666
Max Act: 4.8166. Min Act: -0.1700
Data Index: 473560 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0666. Min Range: -5.0666
Max Act: 4.8166. Min Act: -0.1700
Data Index: 3752767 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0666. Min Range: -5.0666
Max Act: 4.8166. Min Act: -0.1700
Data Index: 5643216 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0666. Min Range: -5.0666
Max Act: 4.8166. Min Act: -0.1700
Data Index: 5381329 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0666. Min Range: -5.0666
Max Act: 4.7854. Min Act: -0.1700
Data Index: 2432217 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0666. Min Range: -5.0666
Max Act: 4.7854. Min Act: -0.1700
Data Index: 1505883 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0666. Min Range: -5.0666
Max Act: 4.7854. Min Act: -0.1700
Data Index: 717152 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0666. Min Range: -5.0666
Max Act: 4.7854. Min Act: -0.1700
Data Index: 4476008 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19