Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3657 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2764. Min Range: -8.2764
Max Act: 8.2764. Min Act: -0.1700
Data Index: 4199848 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2764. Min Range: -8.2764
Max Act: 8.2139. Min Act: -0.1700
Data Index: 4541147 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2764. Min Range: -8.2764
Max Act: 8.2139. Min Act: -0.1700
Data Index: 5928752 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2764. Min Range: -8.2764
Max Act: 8.0889. Min Act: -0.1700
Data Index: 2792319 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2764. Min Range: -8.2764
Max Act: 8.0264. Min Act: -0.1700
Data Index: 873631 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2764. Min Range: -8.2764
Max Act: 7.9014. Min Act: -0.1700
Data Index: 3472997 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2764. Min Range: -8.2764
Max Act: 7.9014. Min Act: -0.1700
Data Index: 198031 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2764. Min Range: -8.2764
Max Act: 7.8389. Min Act: -0.1700
Data Index: 7231550 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2764. Min Range: -8.2764
Max Act: 7.8389. Min Act: -0.1700
Data Index: 5838770 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2764. Min Range: -8.2764
Max Act: 7.7764. Min Act: -0.1700
Data Index: 3669651 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2764. Min Range: -8.2764
Max Act: 7.7764. Min Act: -0.1700
Data Index: 5206366 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2764. Min Range: -8.2764
Max Act: 7.7764. Min Act: -0.1700
Data Index: 4962950 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2764. Min Range: -8.2764
Max Act: 7.7764. Min Act: -0.1700
Data Index: 1935492 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2764. Min Range: -8.2764
Max Act: 7.7139. Min Act: -0.1700
Data Index: 7094458 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2764. Min Range: -8.2764
Max Act: 7.6827. Min Act: -0.1700
Data Index: 3162837 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2764. Min Range: -8.2764
Max Act: 7.6827. Min Act: -0.1700
Data Index: 5093708 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2764. Min Range: -8.2764
Max Act: 7.6514. Min Act: -0.1700
Data Index: 4942262 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2764. Min Range: -8.2764
Max Act: 7.6202. Min Act: -0.1700
Data Index: 136748 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2764. Min Range: -8.2764
Max Act: 7.6514. Min Act: -0.1700
Data Index: 671986 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2764. Min Range: -8.2764
Max Act: 7.6827. Min Act: -0.1700
Data Index: 8663054 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19