Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 618 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5913. Min Range: -10.5913
Max Act: 10.5913. Min Act: -0.1700
Data Index: 6993384 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5913. Min Range: -10.5913
Max Act: 9.9663. Min Act: -0.1700
Data Index: 2178678 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5913. Min Range: -10.5913
Max Act: 9.9038. Min Act: -0.1700
Data Index: 7197946 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5913. Min Range: -10.5913
Max Act: 9.8413. Min Act: -0.1700
Data Index: 961086 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5913. Min Range: -10.5913
Max Act: 9.8413. Min Act: -0.1700
Data Index: 4268114 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5913. Min Range: -10.5913
Max Act: 9.7788. Min Act: -0.1700
Data Index: 5379296 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5913. Min Range: -10.5913
Max Act: 9.7788. Min Act: -0.1700
Data Index: 7042348 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5913. Min Range: -10.5913
Max Act: 9.7163. Min Act: -0.1700
Data Index: 8078841 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5913. Min Range: -10.5913
Max Act: 9.6538. Min Act: -0.1700
Data Index: 5686812 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5913. Min Range: -10.5913
Max Act: 9.6538. Min Act: -0.1700
Data Index: 7873934 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5913. Min Range: -10.5913
Max Act: 9.6538. Min Act: -0.1700
Data Index: 5552033 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5913. Min Range: -10.5913
Max Act: 9.6538. Min Act: -0.1700
Data Index: 2445871 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5913. Min Range: -10.5913
Max Act: 9.6538. Min Act: -0.1700
Data Index: 5759765 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5913. Min Range: -10.5913
Max Act: 9.6538. Min Act: -0.1700
Data Index: 7385026 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5913. Min Range: -10.5913
Max Act: 9.5913. Min Act: -0.1700
Data Index: 3481777 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5913. Min Range: -10.5913
Max Act: 9.5913. Min Act: -0.1700
Data Index: 7303956 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5913. Min Range: -10.5913
Max Act: 9.5288. Min Act: -0.1700
Data Index: 1465569 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5913. Min Range: -10.5913
Max Act: 9.5288. Min Act: -0.1700
Data Index: 2421224 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5913. Min Range: -10.5913
Max Act: 9.5288. Min Act: -0.1700
Data Index: 4041559 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5913. Min Range: -10.5913
Max Act: 9.5288. Min Act: -0.1700
Data Index: 7722815 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19