Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3284 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0583. Min Range: -7.0583
Max Act: 7.0583. Min Act: -0.1700
Data Index: 5537262 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0583. Min Range: -7.0583
Max Act: 7.0583. Min Act: -0.1700
Data Index: 391964 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0583. Min Range: -7.0583
Max Act: 6.9333. Min Act: -0.1700
Data Index: 5422758 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0583. Min Range: -7.0583
Max Act: 6.9021. Min Act: -0.1700
Data Index: 7343709 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0583. Min Range: -7.0583
Max Act: 6.9021. Min Act: -0.1700
Data Index: 6545558 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0583. Min Range: -7.0583
Max Act: 6.8708. Min Act: -0.1700
Data Index: 2392741 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0583. Min Range: -7.0583
Max Act: 6.8396. Min Act: -0.1700
Data Index: 8721895 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0583. Min Range: -7.0583
Max Act: 6.8708. Min Act: -0.1700
Data Index: 6571039 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0583. Min Range: -7.0583
Max Act: 6.8396. Min Act: -0.1700
Data Index: 2322436 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0583. Min Range: -7.0583
Max Act: 6.8396. Min Act: -0.1700
Data Index: 4583816 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0583. Min Range: -7.0583
Max Act: 6.8396. Min Act: -0.1700
Data Index: 2332481 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0583. Min Range: -7.0583
Max Act: 6.8083. Min Act: -0.1700
Data Index: 618307 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0583. Min Range: -7.0583
Max Act: 6.7771. Min Act: -0.1700
Data Index: 6603363 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0583. Min Range: -7.0583
Max Act: 6.8083. Min Act: -0.1700
Data Index: 6959422 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0583. Min Range: -7.0583
Max Act: 6.8083. Min Act: -0.1700
Data Index: 3101159 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0583. Min Range: -7.0583
Max Act: 6.8083. Min Act: -0.1700
Data Index: 4516990 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0583. Min Range: -7.0583
Max Act: 6.8083. Min Act: -0.1700
Data Index: 5845833 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0583. Min Range: -7.0583
Max Act: 6.8083. Min Act: -0.1700
Data Index: 6341659 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0583. Min Range: -7.0583
Max Act: 6.8083. Min Act: -0.1700
Data Index: 3223173 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0583. Min Range: -7.0583
Max Act: 6.8083. Min Act: -0.1700
Data Index: 5973171 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #19