Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3341 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0073. Min Range: -5.0073
Max Act: 5.0073. Min Act: -0.1700
Data Index: 538800 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0073. Min Range: -5.0073
Max Act: 5.0073. Min Act: -0.1700
Data Index: 7774049 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0073. Min Range: -5.0073
Max Act: 5.0073. Min Act: -0.1700
Data Index: 7774047 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0073. Min Range: -5.0073
Max Act: 4.9760. Min Act: -0.1700
Data Index: 7755810 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0073. Min Range: -5.0073
Max Act: 4.9448. Min Act: -0.1700
Data Index: 7137553 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0073. Min Range: -5.0073
Max Act: 4.9448. Min Act: -0.1700
Data Index: 2435306 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0073. Min Range: -5.0073
Max Act: 4.9135. Min Act: -0.1700
Data Index: 3877141 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0073. Min Range: -5.0073
Max Act: 4.9135. Min Act: -0.1700
Data Index: 3687693 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0073. Min Range: -5.0073
Max Act: 4.9135. Min Act: -0.1700
Data Index: 7814180 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0073. Min Range: -5.0073
Max Act: 4.8823. Min Act: -0.1700
Data Index: 669648 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0073. Min Range: -5.0073
Max Act: 4.8823. Min Act: -0.1700
Data Index: 4869470 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0073. Min Range: -5.0073
Max Act: 4.8823. Min Act: -0.1700
Data Index: 5486743 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0073. Min Range: -5.0073
Max Act: 4.8823. Min Act: -0.1700
Data Index: 807432 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0073. Min Range: -5.0073
Max Act: 4.8823. Min Act: -0.1700
Data Index: 5913639 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0073. Min Range: -5.0073
Max Act: 4.8823. Min Act: -0.1700
Data Index: 7388025 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0073. Min Range: -5.0073
Max Act: 4.8823. Min Act: -0.1700
Data Index: 7603255 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0073. Min Range: -5.0073
Max Act: 4.8823. Min Act: -0.1700
Data Index: 3450405 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0073. Min Range: -5.0073
Max Act: 4.8823. Min Act: -0.1700
Data Index: 4849320 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0073. Min Range: -5.0073
Max Act: 4.8823. Min Act: -0.1700
Data Index: 4676031 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0073. Min Range: -5.0073
Max Act: 4.8823. Min Act: -0.1700
Data Index: 7774052 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #19