Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2965 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5977. Min Range: -9.5977
Max Act: 9.5977. Min Act: -0.1700
Data Index: 5425032 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5977. Min Range: -9.5977
Max Act: 9.5352. Min Act: -0.1700
Data Index: 4517154 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5977. Min Range: -9.5977
Max Act: 9.5352. Min Act: -0.1700
Data Index: 7737337 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5977. Min Range: -9.5977
Max Act: 9.2227. Min Act: -0.1700
Data Index: 2451880 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5977. Min Range: -9.5977
Max Act: 9.0977. Min Act: -0.1700
Data Index: 5788638 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5977. Min Range: -9.5977
Max Act: 8.9102. Min Act: -0.1700
Data Index: 2182665 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5977. Min Range: -9.5977
Max Act: 8.8477. Min Act: -0.1700
Data Index: 7122263 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5977. Min Range: -9.5977
Max Act: 8.8477. Min Act: -0.1700
Data Index: 46026 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5977. Min Range: -9.5977
Max Act: 8.9102. Min Act: -0.1700
Data Index: 3430968 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5977. Min Range: -9.5977
Max Act: 8.9102. Min Act: -0.1700
Data Index: 2055175 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5977. Min Range: -9.5977
Max Act: 8.8477. Min Act: -0.1700
Data Index: 5385886 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5977. Min Range: -9.5977
Max Act: 8.9102. Min Act: -0.1700
Data Index: 8458961 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5977. Min Range: -9.5977
Max Act: 8.7852. Min Act: -0.1700
Data Index: 3031936 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5977. Min Range: -9.5977
Max Act: 8.7227. Min Act: -0.1700
Data Index: 2645151 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5977. Min Range: -9.5977
Max Act: 8.7852. Min Act: -0.1700
Data Index: 785688 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5977. Min Range: -9.5977
Max Act: 8.7852. Min Act: -0.1700
Data Index: 8381294 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5977. Min Range: -9.5977
Max Act: 8.7852. Min Act: -0.1700
Data Index: 7344571 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5977. Min Range: -9.5977
Max Act: 8.7227. Min Act: -0.1700
Data Index: 901817 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5977. Min Range: -9.5977
Max Act: 8.7227. Min Act: -0.1700
Data Index: 5703534 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5977. Min Range: -9.5977
Max Act: 8.7227. Min Act: -0.1700
Data Index: 6165773 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #19