Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6189 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0081. Min Range: -5.0081
Max Act: 5.0081. Min Act: -0.1700
Data Index: 202860 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0081. Min Range: -5.0081
Max Act: 4.9768. Min Act: -0.1700
Data Index: 202863 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0081. Min Range: -5.0081
Max Act: 5.0081. Min Act: -0.1700
Data Index: 2546355 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0081. Min Range: -5.0081
Max Act: 4.9768. Min Act: -0.1700
Data Index: 8782392 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0081. Min Range: -5.0081
Max Act: 4.9456. Min Act: -0.1700
Data Index: 888836 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0081. Min Range: -5.0081
Max Act: 4.9143. Min Act: -0.1700
Data Index: 4102471 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0081. Min Range: -5.0081
Max Act: 4.9143. Min Act: -0.1700
Data Index: 111167 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0081. Min Range: -5.0081
Max Act: 4.9143. Min Act: -0.1700
Data Index: 7306940 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0081. Min Range: -5.0081
Max Act: 4.9143. Min Act: -0.1700
Data Index: 6822991 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0081. Min Range: -5.0081
Max Act: 4.8831. Min Act: -0.1700
Data Index: 7475955 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0081. Min Range: -5.0081
Max Act: 4.8831. Min Act: -0.1700
Data Index: 502574 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0081. Min Range: -5.0081
Max Act: 4.8518. Min Act: -0.1700
Data Index: 4102472 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0081. Min Range: -5.0081
Max Act: 4.8518. Min Act: -0.1700
Data Index: 2467817 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0081. Min Range: -5.0081
Max Act: 4.8518. Min Act: -0.1700
Data Index: 2923595 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0081. Min Range: -5.0081
Max Act: 4.8518. Min Act: -0.1700
Data Index: 3845333 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0081. Min Range: -5.0081
Max Act: 4.8518. Min Act: -0.1700
Data Index: 3845330 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0081. Min Range: -5.0081
Max Act: 4.8518. Min Act: -0.1700
Data Index: 6021943 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0081. Min Range: -5.0081
Max Act: 4.8206. Min Act: -0.1700
Data Index: 199743 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0081. Min Range: -5.0081
Max Act: 4.7893. Min Act: -0.1700
Data Index: 5281884 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0081. Min Range: -5.0081
Max Act: 4.7893. Min Act: -0.1700
Data Index: 3843196 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #19