Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2879 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1874. Min Range: -9.1874
Max Act: 9.1874. Min Act: -0.1700
Data Index: 1144742 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1874. Min Range: -9.1874
Max Act: 8.9999. Min Act: -0.1700
Data Index: 1883316 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1874. Min Range: -9.1874
Max Act: 8.9374. Min Act: -0.1700
Data Index: 5007495 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1874. Min Range: -9.1874
Max Act: 8.9374. Min Act: -0.1700
Data Index: 6971530 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1874. Min Range: -9.1874
Max Act: 8.9374. Min Act: -0.1700
Data Index: 8332463 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1874. Min Range: -9.1874
Max Act: 8.9374. Min Act: -0.1700
Data Index: 3701246 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1874. Min Range: -9.1874
Max Act: 8.8749. Min Act: -0.1700
Data Index: 6908021 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1874. Min Range: -9.1874
Max Act: 8.8124. Min Act: -0.1700
Data Index: 6895871 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1874. Min Range: -9.1874
Max Act: 8.7499. Min Act: -0.1700
Data Index: 7326961 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1874. Min Range: -9.1874
Max Act: 8.7499. Min Act: -0.1700
Data Index: 384824 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1874. Min Range: -9.1874
Max Act: 8.7499. Min Act: -0.1700
Data Index: 8569514 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1874. Min Range: -9.1874
Max Act: 8.6874. Min Act: -0.1700
Data Index: 338619 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1874. Min Range: -9.1874
Max Act: 8.6874. Min Act: -0.1700
Data Index: 5648620 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1874. Min Range: -9.1874
Max Act: 8.6249. Min Act: -0.1700
Data Index: 6129336 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1874. Min Range: -9.1874
Max Act: 8.6249. Min Act: -0.1700
Data Index: 653416 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1874. Min Range: -9.1874
Max Act: 8.5624. Min Act: -0.1700
Data Index: 5857 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1874. Min Range: -9.1874
Max Act: 8.5624. Min Act: -0.1700
Data Index: 8449073 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1874. Min Range: -9.1874
Max Act: 8.5624. Min Act: -0.1700
Data Index: 1558525 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1874. Min Range: -9.1874
Max Act: 8.5624. Min Act: -0.1700
Data Index: 2331732 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1874. Min Range: -9.1874
Max Act: 8.5624. Min Act: -0.1700
Data Index: 415253 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #19