Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5746 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8721. Min Range: -8.8721
Max Act: 8.8721. Min Act: -0.1700
Data Index: 3299571 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8721. Min Range: -8.8721
Max Act: 8.6221. Min Act: -0.1700
Data Index: 583202 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8721. Min Range: -8.8721
Max Act: 8.5596. Min Act: -0.1700
Data Index: 3281237 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8721. Min Range: -8.8721
Max Act: 8.4971. Min Act: -0.1700
Data Index: 6095863 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8721. Min Range: -8.8721
Max Act: 8.4971. Min Act: -0.1700
Data Index: 8156568 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8721. Min Range: -8.8721
Max Act: 8.4971. Min Act: -0.1700
Data Index: 4870020 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8721. Min Range: -8.8721
Max Act: 8.4346. Min Act: -0.1700
Data Index: 6433031 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8721. Min Range: -8.8721
Max Act: 8.4346. Min Act: -0.1700
Data Index: 672116 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8721. Min Range: -8.8721
Max Act: 8.4346. Min Act: -0.1700
Data Index: 3248666 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8721. Min Range: -8.8721
Max Act: 8.3721. Min Act: -0.1700
Data Index: 5594070 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8721. Min Range: -8.8721
Max Act: 8.3721. Min Act: -0.1700
Data Index: 1082093 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8721. Min Range: -8.8721
Max Act: 8.3096. Min Act: -0.1700
Data Index: 7558689 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8721. Min Range: -8.8721
Max Act: 8.3096. Min Act: -0.1700
Data Index: 283942 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8721. Min Range: -8.8721
Max Act: 8.3096. Min Act: -0.1700
Data Index: 8607238 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8721. Min Range: -8.8721
Max Act: 8.3096. Min Act: -0.1700
Data Index: 6587485 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8721. Min Range: -8.8721
Max Act: 8.2471. Min Act: -0.1700
Data Index: 5480138 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8721. Min Range: -8.8721
Max Act: 8.2471. Min Act: -0.1700
Data Index: 6176031 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8721. Min Range: -8.8721
Max Act: 8.1846. Min Act: -0.1700
Data Index: 5421499 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8721. Min Range: -8.8721
Max Act: 8.2471. Min Act: -0.1700
Data Index: 7478842 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8721. Min Range: -8.8721
Max Act: 8.2471. Min Act: -0.1700
Data Index: 6961925 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #19