Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3082 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2124. Min Range: -5.2124
Max Act: 5.2124. Min Act: -0.1700
Data Index: 1689670 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2124. Min Range: -5.2124
Max Act: 5.1186. Min Act: -0.1700
Data Index: 5613267 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2124. Min Range: -5.2124
Max Act: 5.1186. Min Act: -0.1700
Data Index: 6122677 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2124. Min Range: -5.2124
Max Act: 5.0874. Min Act: -0.1700
Data Index: 156442 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2124. Min Range: -5.2124
Max Act: 5.0874. Min Act: -0.1700
Data Index: 4909673 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2124. Min Range: -5.2124
Max Act: 5.0561. Min Act: -0.1700
Data Index: 334897 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2124. Min Range: -5.2124
Max Act: 5.0561. Min Act: -0.1700
Data Index: 4873153 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2124. Min Range: -5.2124
Max Act: 5.0561. Min Act: -0.1700
Data Index: 7116125 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2124. Min Range: -5.2124
Max Act: 5.0561. Min Act: -0.1700
Data Index: 1222016 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2124. Min Range: -5.2124
Max Act: 5.0561. Min Act: -0.1700
Data Index: 4873151 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2124. Min Range: -5.2124
Max Act: 5.0249. Min Act: -0.1700
Data Index: 4396439 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2124. Min Range: -5.2124
Max Act: 5.0249. Min Act: -0.1700
Data Index: 7415113 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2124. Min Range: -5.2124
Max Act: 5.0249. Min Act: -0.1700
Data Index: 3668153 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2124. Min Range: -5.2124
Max Act: 5.0249. Min Act: -0.1700
Data Index: 6242619 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2124. Min Range: -5.2124
Max Act: 4.9936. Min Act: -0.1700
Data Index: 2125209 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2124. Min Range: -5.2124
Max Act: 4.9936. Min Act: -0.1700
Data Index: 6579629 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2124. Min Range: -5.2124
Max Act: 4.9936. Min Act: -0.1700
Data Index: 4195190 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2124. Min Range: -5.2124
Max Act: 4.9936. Min Act: -0.1700
Data Index: 3449009 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2124. Min Range: -5.2124
Max Act: 4.9624. Min Act: -0.1700
Data Index: 3893680 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2124. Min Range: -5.2124
Max Act: 5.0249. Min Act: -0.1700
Data Index: 2697086 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #19