Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 703 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5674. Min Range: -5.5674
Max Act: 5.5674. Min Act: -0.1700
Data Index: 5101117 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5674. Min Range: -5.5674
Max Act: 5.5674. Min Act: -0.1700
Data Index: 2171203 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5674. Min Range: -5.5674
Max Act: 5.5361. Min Act: -0.1700
Data Index: 840257 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5674. Min Range: -5.5674
Max Act: 5.5361. Min Act: -0.1700
Data Index: 7788043 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5674. Min Range: -5.5674
Max Act: 5.5049. Min Act: -0.1700
Data Index: 4850858 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5674. Min Range: -5.5674
Max Act: 5.4736. Min Act: -0.1700
Data Index: 8352234 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5674. Min Range: -5.5674
Max Act: 5.4736. Min Act: -0.1700
Data Index: 5823145 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5674. Min Range: -5.5674
Max Act: 5.4736. Min Act: -0.1700
Data Index: 6991077 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5674. Min Range: -5.5674
Max Act: 5.4424. Min Act: -0.1700
Data Index: 6991078 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5674. Min Range: -5.5674
Max Act: 5.4424. Min Act: -0.1700
Data Index: 2170197 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5674. Min Range: -5.5674
Max Act: 5.4424. Min Act: -0.1700
Data Index: 6696737 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5674. Min Range: -5.5674
Max Act: 5.4424. Min Act: -0.1700
Data Index: 2336967 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5674. Min Range: -5.5674
Max Act: 5.4424. Min Act: -0.1700
Data Index: 3027206 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5674. Min Range: -5.5674
Max Act: 5.4424. Min Act: -0.1700
Data Index: 5841546 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5674. Min Range: -5.5674
Max Act: 5.4424. Min Act: -0.1700
Data Index: 5841545 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5674. Min Range: -5.5674
Max Act: 5.4424. Min Act: -0.1700
Data Index: 3430139 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5674. Min Range: -5.5674
Max Act: 5.4111. Min Act: -0.1700
Data Index: 7649798 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5674. Min Range: -5.5674
Max Act: 5.4111. Min Act: -0.1700
Data Index: 4243004 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5674. Min Range: -5.5674
Max Act: 5.4424. Min Act: -0.1700
Data Index: 5357983 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5674. Min Range: -5.5674
Max Act: 5.4111. Min Act: -0.1700
Data Index: 8152342 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19