Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2609 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0265. Min Range: -3.0265
Max Act: 3.0265. Min Act: -0.1700
Data Index: 5426074 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0265. Min Range: -3.0265
Max Act: 3.0107. Min Act: -0.1700
Data Index: 4221781 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0265. Min Range: -3.0265
Max Act: 3.0107. Min Act: -0.1700
Data Index: 7571313 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0265. Min Range: -3.0265
Max Act: 2.9949. Min Act: -0.1700
Data Index: 6524711 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0265. Min Range: -3.0265
Max Act: 2.9316. Min Act: -0.1700
Data Index: 7120544 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0265. Min Range: -3.0265
Max Act: 2.9158. Min Act: -0.1700
Data Index: 34835 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0265. Min Range: -3.0265
Max Act: 2.9158. Min Act: -0.1700
Data Index: 6000060 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0265. Min Range: -3.0265
Max Act: 2.9158. Min Act: -0.1700
Data Index: 4607227 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0265. Min Range: -3.0265
Max Act: 2.8999. Min Act: -0.1700
Data Index: 6098195 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0265. Min Range: -3.0265
Max Act: 2.8840. Min Act: -0.1700
Data Index: 4935794 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0265. Min Range: -3.0265
Max Act: 2.8840. Min Act: -0.1700
Data Index: 3212124 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0265. Min Range: -3.0265
Max Act: 2.8999. Min Act: -0.1700
Data Index: 7313246 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0265. Min Range: -3.0265
Max Act: 2.8840. Min Act: -0.1700
Data Index: 3441386 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0265. Min Range: -3.0265
Max Act: 2.8840. Min Act: -0.1700
Data Index: 6450592 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0265. Min Range: -3.0265
Max Act: 2.8840. Min Act: -0.1700
Data Index: 8397268 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0265. Min Range: -3.0265
Max Act: 2.8840. Min Act: -0.1700
Data Index: 1717851 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0265. Min Range: -3.0265
Max Act: 2.8682. Min Act: -0.1700
Data Index: 4778879 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0265. Min Range: -3.0265
Max Act: 2.8682. Min Act: -0.1700
Data Index: 832053 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0265. Min Range: -3.0265
Max Act: 2.8682. Min Act: -0.1700
Data Index: 1308122 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0265. Min Range: -3.0265
Max Act: 2.8682. Min Act: -0.1700
Data Index: 6409332 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19