Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2087 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6853. Min Range: -2.6853
Max Act: 2.6853. Min Act: -0.1700
Data Index: 7105421 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6853. Min Range: -2.6853
Max Act: 2.5728. Min Act: -0.1700
Data Index: 8219976 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6853. Min Range: -2.6853
Max Act: 2.5728. Min Act: -0.1700
Data Index: 4986143 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6853. Min Range: -2.6853
Max Act: 2.5406. Min Act: -0.1700
Data Index: 4480630 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6853. Min Range: -2.6853
Max Act: 2.5244. Min Act: -0.1700
Data Index: 5582867 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6853. Min Range: -2.6853
Max Act: 2.5244. Min Act: -0.1700
Data Index: 719949 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6853. Min Range: -2.6853
Max Act: 2.5082. Min Act: -0.1700
Data Index: 7980386 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6853. Min Range: -2.6853
Max Act: 2.5082. Min Act: -0.1700
Data Index: 113721 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6853. Min Range: -2.6853
Max Act: 2.5082. Min Act: -0.1700
Data Index: 994754 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6853. Min Range: -2.6853
Max Act: 2.4758. Min Act: -0.1553
Data Index: 4276199 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6853. Min Range: -2.6853
Max Act: 2.4758. Min Act: -0.1700
Data Index: 8333836 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6853. Min Range: -2.6853
Max Act: 2.4920. Min Act: -0.1700
Data Index: 797841 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6853. Min Range: -2.6853
Max Act: 2.4920. Min Act: -0.1700
Data Index: 2089328 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6853. Min Range: -2.6853
Max Act: 2.4920. Min Act: -0.1700
Data Index: 3679613 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6853. Min Range: -2.6853
Max Act: 2.4920. Min Act: -0.1700
Data Index: 2118207 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6853. Min Range: -2.6853
Max Act: 2.4758. Min Act: -0.1700
Data Index: 797842 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6853. Min Range: -2.6853
Max Act: 2.4758. Min Act: -0.1700
Data Index: 7679252 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6853. Min Range: -2.6853
Max Act: 2.4758. Min Act: -0.1700
Data Index: 7295129 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6853. Min Range: -2.6853
Max Act: 2.4758. Min Act: -0.1700
Data Index: 1293005 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6853. Min Range: -2.6853
Max Act: 2.4758. Min Act: -0.1700
Data Index: 2118209 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #19