Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4770 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.8914. Min Range: -11.8914
Max Act: 11.8914. Min Act: -0.1700
Data Index: 770419 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.8914. Min Range: -11.8914
Max Act: 11.6414. Min Act: -0.1700
Data Index: 827316 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.8914. Min Range: -11.8914
Max Act: 11.5789. Min Act: -0.1700
Data Index: 205742 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.8914. Min Range: -11.8914
Max Act: 11.5789. Min Act: -0.1700
Data Index: 1547272 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.8914. Min Range: -11.8914
Max Act: 11.5789. Min Act: -0.1700
Data Index: 8643895 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.8914. Min Range: -11.8914
Max Act: 11.5164. Min Act: -0.1700
Data Index: 2688829 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.8914. Min Range: -11.8914
Max Act: 11.5164. Min Act: -0.1700
Data Index: 5500560 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.8914. Min Range: -11.8914
Max Act: 11.3914. Min Act: -0.1700
Data Index: 918354 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.8914. Min Range: -11.8914
Max Act: 11.4539. Min Act: -0.1700
Data Index: 1060403 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.8914. Min Range: -11.8914
Max Act: 11.3289. Min Act: -0.1700
Data Index: 8171118 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.8914. Min Range: -11.8914
Max Act: 11.4539. Min Act: -0.1700
Data Index: 3664633 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.8914. Min Range: -11.8914
Max Act: 11.3914. Min Act: -0.1700
Data Index: 261825 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.8914. Min Range: -11.8914
Max Act: 11.3914. Min Act: -0.1700
Data Index: 2562647 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.8914. Min Range: -11.8914
Max Act: 11.3289. Min Act: -0.1700
Data Index: 8831270 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.8914. Min Range: -11.8914
Max Act: 11.2664. Min Act: -0.1700
Data Index: 8182456 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.8914. Min Range: -11.8914
Max Act: 11.2039. Min Act: -0.1700
Data Index: 1245456 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.8914. Min Range: -11.8914
Max Act: 11.2039. Min Act: -0.1700
Data Index: 3151835 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.8914. Min Range: -11.8914
Max Act: 11.2039. Min Act: -0.1700
Data Index: 2531458 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.8914. Min Range: -11.8914
Max Act: 11.2664. Min Act: -0.1700
Data Index: 7160363 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.8914. Min Range: -11.8914
Max Act: 11.2039. Min Act: -0.1700
Data Index: 7760124 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #19