Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5539 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7902. Min Range: -2.7902
Max Act: 2.7902. Min Act: -0.1700
Data Index: 463265 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7902. Min Range: -2.7902
Max Act: 2.6302. Min Act: -0.1700
Data Index: 4864570 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7902. Min Range: -2.7902
Max Act: 2.5981. Min Act: -0.1700
Data Index: 3115450 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7902. Min Range: -2.7902
Max Act: 2.5981. Min Act: -0.1700
Data Index: 222881 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7902. Min Range: -2.7902
Max Act: 2.5981. Min Act: -0.1700
Data Index: 4864568 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7902. Min Range: -2.7902
Max Act: 2.5659. Min Act: -0.1700
Data Index: 3386863 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7902. Min Range: -2.7902
Max Act: 2.5659. Min Act: -0.1700
Data Index: 2992323 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7902. Min Range: -2.7902
Max Act: 2.5659. Min Act: -0.1700
Data Index: 1214461 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7902. Min Range: -2.7902
Max Act: 2.5497. Min Act: -0.1700
Data Index: 2668590 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7902. Min Range: -2.7902
Max Act: 2.5174. Min Act: -0.1700
Data Index: 5003003 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7902. Min Range: -2.7902
Max Act: 2.5174. Min Act: -0.1700
Data Index: 4864567 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7902. Min Range: -2.7902
Max Act: 2.5012. Min Act: -0.1700
Data Index: 6099757 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7902. Min Range: -2.7902
Max Act: 2.5012. Min Act: -0.1700
Data Index: 8778955 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7902. Min Range: -2.7902
Max Act: 2.5174. Min Act: -0.1700
Data Index: 257554 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7902. Min Range: -2.7902
Max Act: 2.5012. Min Act: -0.1700
Data Index: 6689506 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7902. Min Range: -2.7902
Max Act: 2.4850. Min Act: -0.1700
Data Index: 8363539 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7902. Min Range: -2.7902
Max Act: 2.5012. Min Act: -0.1700
Data Index: 5609795 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7902. Min Range: -2.7902
Max Act: 2.4850. Min Act: -0.1700
Data Index: 6278872 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7902. Min Range: -2.7902
Max Act: 2.4850. Min Act: -0.1700
Data Index: 564300 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7902. Min Range: -2.7902
Max Act: 2.4525. Min Act: -0.1700
Data Index: 3672486 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #19