Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1898 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0838. Min Range: -6.0838
Max Act: 6.0526. Min Act: -0.1700
Data Index: 1484969 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0838. Min Range: -6.0838
Max Act: 6.0838. Min Act: -0.1700
Data Index: 7039700 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0838. Min Range: -6.0838
Max Act: 5.9588. Min Act: -0.1700
Data Index: 8764881 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0838. Min Range: -6.0838
Max Act: 5.8651. Min Act: -0.1700
Data Index: 1198956 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0838. Min Range: -6.0838
Max Act: 5.8651. Min Act: -0.1700
Data Index: 1899603 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0838. Min Range: -6.0838
Max Act: 5.8026. Min Act: -0.1700
Data Index: 3807693 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0838. Min Range: -6.0838
Max Act: 5.8338. Min Act: -0.1700
Data Index: 1659683 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0838. Min Range: -6.0838
Max Act: 5.7713. Min Act: -0.1700
Data Index: 7390748 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0838. Min Range: -6.0838
Max Act: 5.6463. Min Act: -0.1700
Data Index: 4009856 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0838. Min Range: -6.0838
Max Act: 5.6151. Min Act: -0.1700
Data Index: 1449210 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0838. Min Range: -6.0838
Max Act: 5.6463. Min Act: -0.1700
Data Index: 7699038 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0838. Min Range: -6.0838
Max Act: 5.6151. Min Act: -0.1700
Data Index: 3662067 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0838. Min Range: -6.0838
Max Act: 5.6151. Min Act: -0.1700
Data Index: 8041811 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0838. Min Range: -6.0838
Max Act: 5.5526. Min Act: -0.1700
Data Index: 7311268 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0838. Min Range: -6.0838
Max Act: 5.6151. Min Act: -0.1700
Data Index: 6567313 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0838. Min Range: -6.0838
Max Act: 5.5838. Min Act: -0.1700
Data Index: 1187269 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0838. Min Range: -6.0838
Max Act: 5.5838. Min Act: -0.1700
Data Index: 6223870 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0838. Min Range: -6.0838
Max Act: 5.5526. Min Act: -0.1700
Data Index: 8258043 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0838. Min Range: -6.0838
Max Act: 5.5838. Min Act: -0.1700
Data Index: 7741813 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0838. Min Range: -6.0838
Max Act: 5.5838. Min Act: -0.1700
Data Index: 7860600 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #19