Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1114 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0183. Min Range: -5.0183
Max Act: 5.0183. Min Act: -0.1700
Data Index: 3219061 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0183. Min Range: -5.0183
Max Act: 4.9246. Min Act: -0.1700
Data Index: 783912 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0183. Min Range: -5.0183
Max Act: 4.9246. Min Act: -0.1700
Data Index: 634849 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0183. Min Range: -5.0183
Max Act: 4.9246. Min Act: -0.1700
Data Index: 2384974 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0183. Min Range: -5.0183
Max Act: 4.9246. Min Act: -0.1700
Data Index: 1607640 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0183. Min Range: -5.0183
Max Act: 4.9246. Min Act: -0.1700
Data Index: 1859215 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0183. Min Range: -5.0183
Max Act: 4.9246. Min Act: -0.1700
Data Index: 2584613 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0183. Min Range: -5.0183
Max Act: 4.9246. Min Act: -0.1700
Data Index: 2384362 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0183. Min Range: -5.0183
Max Act: 4.9246. Min Act: -0.1700
Data Index: 2308418 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0183. Min Range: -5.0183
Max Act: 4.9246. Min Act: -0.1700
Data Index: 2248572 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0183. Min Range: -5.0183
Max Act: 4.9246. Min Act: -0.1700
Data Index: 1713787 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0183. Min Range: -5.0183
Max Act: 4.9246. Min Act: -0.1700
Data Index: 644431 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0183. Min Range: -5.0183
Max Act: 4.9246. Min Act: -0.1700
Data Index: 979208 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0183. Min Range: -5.0183
Max Act: 4.9246. Min Act: -0.1700
Data Index: 1627002 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0183. Min Range: -5.0183
Max Act: 4.9246. Min Act: -0.1700
Data Index: 725043 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0183. Min Range: -5.0183
Max Act: 4.9246. Min Act: -0.1700
Data Index: 721982 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0183. Min Range: -5.0183
Max Act: 4.9246. Min Act: -0.1700
Data Index: 2577826 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0183. Min Range: -5.0183
Max Act: 4.9246. Min Act: -0.1700
Data Index: 3030793 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0183. Min Range: -5.0183
Max Act: 4.9246. Min Act: -0.1700
Data Index: 2773856 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0183. Min Range: -5.0183
Max Act: 4.9246. Min Act: -0.1700
Data Index: 2162905 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19