Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1890 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5438. Min Range: -7.5438
Max Act: 7.5438. Min Act: -0.1700
Data Index: 401432 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5438. Min Range: -7.5438
Max Act: 7.3875. Min Act: -0.1700
Data Index: 7184147 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5438. Min Range: -7.5438
Max Act: 7.3563. Min Act: -0.1700
Data Index: 8027820 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5438. Min Range: -7.5438
Max Act: 7.2625. Min Act: -0.1700
Data Index: 1544616 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5438. Min Range: -7.5438
Max Act: 7.2313. Min Act: -0.1700
Data Index: 4767192 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5438. Min Range: -7.5438
Max Act: 7.1688. Min Act: -0.1700
Data Index: 1717272 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5438. Min Range: -7.5438
Max Act: 7.1688. Min Act: -0.1700
Data Index: 4306004 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5438. Min Range: -7.5438
Max Act: 7.1063. Min Act: -0.1700
Data Index: 5707933 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5438. Min Range: -7.5438
Max Act: 7.1063. Min Act: -0.1700
Data Index: 1534723 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5438. Min Range: -7.5438
Max Act: 7.0438. Min Act: -0.1700
Data Index: 3272000 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5438. Min Range: -7.5438
Max Act: 7.0438. Min Act: -0.1700
Data Index: 5043189 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5438. Min Range: -7.5438
Max Act: 7.0125. Min Act: -0.1700
Data Index: 6363318 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5438. Min Range: -7.5438
Max Act: 7.0125. Min Act: -0.1700
Data Index: 4345862 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5438. Min Range: -7.5438
Max Act: 6.9813. Min Act: -0.1700
Data Index: 7609089 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5438. Min Range: -7.5438
Max Act: 6.9813. Min Act: -0.1700
Data Index: 1139853 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5438. Min Range: -7.5438
Max Act: 6.9188. Min Act: -0.1700
Data Index: 3371867 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5438. Min Range: -7.5438
Max Act: 6.9188. Min Act: -0.1700
Data Index: 1139908 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5438. Min Range: -7.5438
Max Act: 6.9188. Min Act: -0.1700
Data Index: 4402205 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5438. Min Range: -7.5438
Max Act: 6.8875. Min Act: -0.1700
Data Index: 7355683 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5438. Min Range: -7.5438
Max Act: 6.8563. Min Act: -0.1700
Data Index: 661533 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #19