Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 651 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5620. Min Range: -7.5620
Max Act: 7.5620. Min Act: -0.1700
Data Index: 7316108 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5620. Min Range: -7.5620
Max Act: 7.5620. Min Act: -0.1700
Data Index: 4739991 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5620. Min Range: -7.5620
Max Act: 7.3745. Min Act: -0.1700
Data Index: 3408155 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5620. Min Range: -7.5620
Max Act: 7.3120. Min Act: -0.1700
Data Index: 3663169 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5620. Min Range: -7.5620
Max Act: 7.3433. Min Act: -0.1700
Data Index: 4300298 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5620. Min Range: -7.5620
Max Act: 7.2808. Min Act: -0.1700
Data Index: 1786405 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5620. Min Range: -7.5620
Max Act: 7.2808. Min Act: -0.1700
Data Index: 5539109 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5620. Min Range: -7.5620
Max Act: 7.2808. Min Act: -0.1700
Data Index: 1668506 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5620. Min Range: -7.5620
Max Act: 7.2495. Min Act: -0.1700
Data Index: 7185811 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5620. Min Range: -7.5620
Max Act: 7.2495. Min Act: -0.1700
Data Index: 266882 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5620. Min Range: -7.5620
Max Act: 7.2183. Min Act: -0.1700
Data Index: 8260758 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5620. Min Range: -7.5620
Max Act: 7.1870. Min Act: -0.1700
Data Index: 1306996 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5620. Min Range: -7.5620
Max Act: 7.1870. Min Act: -0.1700
Data Index: 3157305 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5620. Min Range: -7.5620
Max Act: 7.1870. Min Act: -0.1700
Data Index: 782056 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5620. Min Range: -7.5620
Max Act: 7.1870. Min Act: -0.1700
Data Index: 40048 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5620. Min Range: -7.5620
Max Act: 7.1558. Min Act: -0.1700
Data Index: 484918 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5620. Min Range: -7.5620
Max Act: 7.1558. Min Act: -0.1700
Data Index: 4848869 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5620. Min Range: -7.5620
Max Act: 7.1558. Min Act: -0.1700
Data Index: 2832296 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5620. Min Range: -7.5620
Max Act: 7.1558. Min Act: -0.1700
Data Index: 7556102 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5620. Min Range: -7.5620
Max Act: 7.1558. Min Act: -0.1700
Data Index: 7290540 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #19