Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5442 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4894. Min Range: -9.4894
Max Act: 9.4894. Min Act: -0.1700
Data Index: 4316719 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4894. Min Range: -9.4894
Max Act: 9.4269. Min Act: -0.1700
Data Index: 7509478 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4894. Min Range: -9.4894
Max Act: 9.3644. Min Act: -0.1700
Data Index: 4790565 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4894. Min Range: -9.4894
Max Act: 9.3019. Min Act: -0.1700
Data Index: 7458661 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4894. Min Range: -9.4894
Max Act: 9.2394. Min Act: -0.1700
Data Index: 7419762 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4894. Min Range: -9.4894
Max Act: 9.1769. Min Act: -0.1700
Data Index: 2849447 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4894. Min Range: -9.4894
Max Act: 9.0519. Min Act: -0.1700
Data Index: 4874169 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4894. Min Range: -9.4894
Max Act: 9.0519. Min Act: -0.1700
Data Index: 997357 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4894. Min Range: -9.4894
Max Act: 9.1144. Min Act: -0.1700
Data Index: 1044691 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4894. Min Range: -9.4894
Max Act: 9.0519. Min Act: -0.1700
Data Index: 1687292 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4894. Min Range: -9.4894
Max Act: 9.0519. Min Act: -0.1700
Data Index: 900061 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4894. Min Range: -9.4894
Max Act: 9.0519. Min Act: -0.1700
Data Index: 6951848 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4894. Min Range: -9.4894
Max Act: 8.9269. Min Act: -0.1700
Data Index: 7504 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4894. Min Range: -9.4894
Max Act: 8.9269. Min Act: -0.1700
Data Index: 8293948 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4894. Min Range: -9.4894
Max Act: 8.9269. Min Act: -0.1700
Data Index: 5471193 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4894. Min Range: -9.4894
Max Act: 8.8644. Min Act: -0.1700
Data Index: 4119885 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4894. Min Range: -9.4894
Max Act: 8.8644. Min Act: -0.1700
Data Index: 1480870 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4894. Min Range: -9.4894
Max Act: 8.8019. Min Act: -0.1700
Data Index: 1305103 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4894. Min Range: -9.4894
Max Act: 8.8019. Min Act: -0.1700
Data Index: 1943577 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4894. Min Range: -9.4894
Max Act: 8.8019. Min Act: -0.1700
Data Index: 2937610 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #19