Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4715 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7601. Min Range: -7.7601
Max Act: 7.7601. Min Act: -0.1700
Data Index: 5051714 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7601. Min Range: -7.7601
Max Act: 7.5101. Min Act: -0.1700
Data Index: 6545847 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7601. Min Range: -7.7601
Max Act: 7.3226. Min Act: -0.1700
Data Index: 4572542 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7601. Min Range: -7.7601
Max Act: 7.3226. Min Act: -0.1700
Data Index: 6573929 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7601. Min Range: -7.7601
Max Act: 7.1351. Min Act: -0.1700
Data Index: 542898 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7601. Min Range: -7.7601
Max Act: 7.0726. Min Act: -0.1700
Data Index: 4788715 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7601. Min Range: -7.7601
Max Act: 7.1038. Min Act: -0.1700
Data Index: 7542155 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7601. Min Range: -7.7601
Max Act: 7.0726. Min Act: -0.1700
Data Index: 817779 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7601. Min Range: -7.7601
Max Act: 6.9476. Min Act: -0.1700
Data Index: 8296613 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7601. Min Range: -7.7601
Max Act: 6.9163. Min Act: -0.1700
Data Index: 348412 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7601. Min Range: -7.7601
Max Act: 6.9163. Min Act: -0.1700
Data Index: 5678632 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7601. Min Range: -7.7601
Max Act: 6.8851. Min Act: -0.1700
Data Index: 8166816 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7601. Min Range: -7.7601
Max Act: 6.8538. Min Act: -0.1700
Data Index: 5012039 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7601. Min Range: -7.7601
Max Act: 6.8851. Min Act: -0.1700
Data Index: 4422806 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7601. Min Range: -7.7601
Max Act: 6.8538. Min Act: -0.1700
Data Index: 3978140 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7601. Min Range: -7.7601
Max Act: 6.8226. Min Act: -0.1700
Data Index: 3481565 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7601. Min Range: -7.7601
Max Act: 6.8226. Min Act: -0.1700
Data Index: 219500 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7601. Min Range: -7.7601
Max Act: 6.7913. Min Act: -0.1700
Data Index: 4310472 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7601. Min Range: -7.7601
Max Act: 6.7601. Min Act: -0.1700
Data Index: 242929 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7601. Min Range: -7.7601
Max Act: 6.7601. Min Act: -0.1700
Data Index: 6359108 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #19