Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 350 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1192. Min Range: -5.1192
Max Act: 5.1192. Min Act: -0.1700
Data Index: 3815684 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1192. Min Range: -5.1192
Max Act: 5.1192. Min Act: -0.1700
Data Index: 8521736 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1192. Min Range: -5.1192
Max Act: 5.1192. Min Act: -0.1700
Data Index: 2546489 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1192. Min Range: -5.1192
Max Act: 5.1192. Min Act: -0.1700
Data Index: 664973 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1192. Min Range: -5.1192
Max Act: 5.1192. Min Act: -0.1700
Data Index: 3211244 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1192. Min Range: -5.1192
Max Act: 5.1192. Min Act: -0.1699
Data Index: 1641212 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1192. Min Range: -5.1192
Max Act: 5.1192. Min Act: -0.1700
Data Index: 6324196 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1192. Min Range: -5.1192
Max Act: 5.1192. Min Act: -0.1700
Data Index: 5339581 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1192. Min Range: -5.1192
Max Act: 5.1192. Min Act: -0.1700
Data Index: 1804827 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1192. Min Range: -5.1192
Max Act: 5.1192. Min Act: -0.1700
Data Index: 4098757 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1192. Min Range: -5.1192
Max Act: 5.0879. Min Act: -0.1700
Data Index: 5755609 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1192. Min Range: -5.1192
Max Act: 5.0879. Min Act: -0.1699
Data Index: 5288046 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1192. Min Range: -5.1192
Max Act: 5.0879. Min Act: -0.1700
Data Index: 2039394 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1192. Min Range: -5.1192
Max Act: 5.0567. Min Act: -0.1700
Data Index: 6109189 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1192. Min Range: -5.1192
Max Act: 5.0567. Min Act: -0.1700
Data Index: 6390018 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1192. Min Range: -5.1192
Max Act: 5.0879. Min Act: -0.1700
Data Index: 3468301 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1192. Min Range: -5.1192
Max Act: 5.0567. Min Act: -0.1700
Data Index: 3014767 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1192. Min Range: -5.1192
Max Act: 5.0254. Min Act: -0.1698
Data Index: 1384764 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1192. Min Range: -5.1192
Max Act: 5.0254. Min Act: -0.1700
Data Index: 2801817 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1192. Min Range: -5.1192
Max Act: 5.0254. Min Act: -0.1700
Data Index: 1697297 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19