Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5422 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1182. Min Range: -6.1182
Max Act: 6.1182. Min Act: -0.1700
Data Index: 3217649 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1182. Min Range: -6.1182
Max Act: 5.9307. Min Act: -0.1700
Data Index: 5918010 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1182. Min Range: -6.1182
Max Act: 5.8369. Min Act: -0.1700
Data Index: 6815780 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1182. Min Range: -6.1182
Max Act: 5.8682. Min Act: -0.1700
Data Index: 6333562 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1182. Min Range: -6.1182
Max Act: 5.8057. Min Act: -0.1700
Data Index: 6878394 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1182. Min Range: -6.1182
Max Act: 5.7432. Min Act: -0.1700
Data Index: 5785845 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1182. Min Range: -6.1182
Max Act: 5.7744. Min Act: -0.1700
Data Index: 2229706 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1182. Min Range: -6.1182
Max Act: 5.7744. Min Act: -0.1700
Data Index: 6663933 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1182. Min Range: -6.1182
Max Act: 5.7432. Min Act: -0.1700
Data Index: 688478 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1182. Min Range: -6.1182
Max Act: 5.6807. Min Act: -0.1700
Data Index: 8443711 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1182. Min Range: -6.1182
Max Act: 5.7119. Min Act: -0.1700
Data Index: 3072831 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1182. Min Range: -6.1182
Max Act: 5.7119. Min Act: -0.1700
Data Index: 6219301 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1182. Min Range: -6.1182
Max Act: 5.6807. Min Act: -0.1700
Data Index: 7030491 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1182. Min Range: -6.1182
Max Act: 5.6807. Min Act: -0.1700
Data Index: 6516509 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1182. Min Range: -6.1182
Max Act: 5.6494. Min Act: -0.1700
Data Index: 2096268 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1182. Min Range: -6.1182
Max Act: 5.6182. Min Act: -0.1700
Data Index: 1894726 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1182. Min Range: -6.1182
Max Act: 5.6182. Min Act: -0.1700
Data Index: 2916203 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1182. Min Range: -6.1182
Max Act: 5.6182. Min Act: -0.1700
Data Index: 4952806 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1182. Min Range: -6.1182
Max Act: 5.6182. Min Act: -0.1700
Data Index: 312014 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1182. Min Range: -6.1182
Max Act: 5.5869. Min Act: -0.1700
Data Index: 6113924 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #19