Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5698 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0526. Min Range: -6.0526
Max Act: 6.0526. Min Act: -0.1700
Data Index: 5084328 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0526. Min Range: -6.0526
Max Act: 5.8963. Min Act: -0.1700
Data Index: 5552261 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0526. Min Range: -6.0526
Max Act: 5.8338. Min Act: -0.1700
Data Index: 3273084 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0526. Min Range: -6.0526
Max Act: 5.8338. Min Act: -0.1700
Data Index: 5427514 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0526. Min Range: -6.0526
Max Act: 5.7401. Min Act: -0.1700
Data Index: 3456871 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0526. Min Range: -6.0526
Max Act: 5.7713. Min Act: -0.1700
Data Index: 3145457 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0526. Min Range: -6.0526
Max Act: 5.7401. Min Act: -0.1700
Data Index: 2927971 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0526. Min Range: -6.0526
Max Act: 5.6776. Min Act: -0.1700
Data Index: 1265031 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0526. Min Range: -6.0526
Max Act: 5.6463. Min Act: -0.1700
Data Index: 5337202 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0526. Min Range: -6.0526
Max Act: 5.6151. Min Act: -0.1700
Data Index: 4408256 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0526. Min Range: -6.0526
Max Act: 5.6151. Min Act: -0.1700
Data Index: 8089342 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0526. Min Range: -6.0526
Max Act: 5.5838. Min Act: -0.1700
Data Index: 1606222 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0526. Min Range: -6.0526
Max Act: 5.5838. Min Act: -0.1700
Data Index: 2048985 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0526. Min Range: -6.0526
Max Act: 5.5838. Min Act: -0.1700
Data Index: 3170683 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0526. Min Range: -6.0526
Max Act: 5.5838. Min Act: -0.1700
Data Index: 1958985 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0526. Min Range: -6.0526
Max Act: 5.5838. Min Act: -0.1700
Data Index: 6010616 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0526. Min Range: -6.0526
Max Act: 5.5526. Min Act: -0.1700
Data Index: 6050369 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0526. Min Range: -6.0526
Max Act: 5.5838. Min Act: -0.1700
Data Index: 1015118 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0526. Min Range: -6.0526
Max Act: 5.5213. Min Act: -0.1700
Data Index: 1351030 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0526. Min Range: -6.0526
Max Act: 5.4901. Min Act: -0.1700
Data Index: 1217143 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #19