Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2728 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1917. Min Range: -8.1917
Max Act: 8.1917. Min Act: -0.1700
Data Index: 882916 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1917. Min Range: -8.1917
Max Act: 8.1292. Min Act: -0.1700
Data Index: 4203814 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1917. Min Range: -8.1917
Max Act: 8.0042. Min Act: -0.1700
Data Index: 6583901 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1917. Min Range: -8.1917
Max Act: 7.8167. Min Act: -0.1700
Data Index: 6814666 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1917. Min Range: -8.1917
Max Act: 7.8167. Min Act: -0.1700
Data Index: 6557448 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1917. Min Range: -8.1917
Max Act: 7.7542. Min Act: -0.1700
Data Index: 3676371 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1917. Min Range: -8.1917
Max Act: 7.7542. Min Act: -0.1700
Data Index: 4086693 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1917. Min Range: -8.1917
Max Act: 7.6917. Min Act: -0.1700
Data Index: 8691438 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1917. Min Range: -8.1917
Max Act: 7.6917. Min Act: -0.1700
Data Index: 859419 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1917. Min Range: -8.1917
Max Act: 7.6917. Min Act: -0.1700
Data Index: 2712894 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1917. Min Range: -8.1917
Max Act: 7.6292. Min Act: -0.1700
Data Index: 2854601 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1917. Min Range: -8.1917
Max Act: 7.6292. Min Act: -0.1700
Data Index: 2963835 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1917. Min Range: -8.1917
Max Act: 7.6292. Min Act: -0.1700
Data Index: 8716803 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1917. Min Range: -8.1917
Max Act: 7.6292. Min Act: -0.1700
Data Index: 8383448 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1917. Min Range: -8.1917
Max Act: 7.6292. Min Act: -0.1700
Data Index: 6856007 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1917. Min Range: -8.1917
Max Act: 7.5667. Min Act: -0.1700
Data Index: 8273285 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1917. Min Range: -8.1917
Max Act: 7.5979. Min Act: -0.1700
Data Index: 3325441 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1917. Min Range: -8.1917
Max Act: 7.5979. Min Act: -0.1700
Data Index: 2090351 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1917. Min Range: -8.1917
Max Act: 7.5979. Min Act: -0.1700
Data Index: 2645126 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1917. Min Range: -8.1917
Max Act: 7.5979. Min Act: -0.1700
Data Index: 4588332 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #19