Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5112 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2710. Min Range: -6.2710
Max Act: 6.2710. Min Act: -0.1700
Data Index: 1994409 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2710. Min Range: -6.2710
Max Act: 5.9898. Min Act: -0.1700
Data Index: 1313348 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2710. Min Range: -6.2710
Max Act: 5.9273. Min Act: -0.1700
Data Index: 2422154 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2710. Min Range: -6.2710
Max Act: 5.8335. Min Act: -0.1700
Data Index: 4177543 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2710. Min Range: -6.2710
Max Act: 5.8335. Min Act: -0.1700
Data Index: 4177545 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2710. Min Range: -6.2710
Max Act: 5.8023. Min Act: -0.1700
Data Index: 8509057 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2710. Min Range: -6.2710
Max Act: 5.8023. Min Act: -0.1700
Data Index: 6318445 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2710. Min Range: -6.2710
Max Act: 5.7085. Min Act: -0.1700
Data Index: 3011011 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2710. Min Range: -6.2710
Max Act: 5.6460. Min Act: -0.1700
Data Index: 2765404 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2710. Min Range: -6.2710
Max Act: 5.6460. Min Act: -0.1700
Data Index: 8329050 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2710. Min Range: -6.2710
Max Act: 5.5523. Min Act: -0.1700
Data Index: 6710446 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2710. Min Range: -6.2710
Max Act: 5.5523. Min Act: -0.1700
Data Index: 1994418 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2710. Min Range: -6.2710
Max Act: 5.5210. Min Act: -0.1700
Data Index: 3425222 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2710. Min Range: -6.2710
Max Act: 5.5523. Min Act: -0.1700
Data Index: 2470904 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2710. Min Range: -6.2710
Max Act: 5.5523. Min Act: -0.1700
Data Index: 2422153 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2710. Min Range: -6.2710
Max Act: 5.5210. Min Act: -0.1700
Data Index: 1651485 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2710. Min Range: -6.2710
Max Act: 5.5210. Min Act: -0.1700
Data Index: 3798445 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2710. Min Range: -6.2710
Max Act: 5.5210. Min Act: -0.1700
Data Index: 1881114 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2710. Min Range: -6.2710
Max Act: 5.4898. Min Act: -0.1700
Data Index: 4885720 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2710. Min Range: -6.2710
Max Act: 5.5210. Min Act: -0.1700
Data Index: 5092754 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #19