Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1314 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1884. Min Range: -5.1884
Max Act: 5.1884. Min Act: -0.1700
Data Index: 474212 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1884. Min Range: -5.1884
Max Act: 5.1572. Min Act: -0.1700
Data Index: 3887738 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1884. Min Range: -5.1884
Max Act: 5.1259. Min Act: -0.1700
Data Index: 5240132 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1884. Min Range: -5.1884
Max Act: 5.1259. Min Act: -0.1700
Data Index: 4774477 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1884. Min Range: -5.1884
Max Act: 5.0947. Min Act: -0.1700
Data Index: 4469112 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1884. Min Range: -5.1884
Max Act: 5.0947. Min Act: -0.1700
Data Index: 7287369 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1884. Min Range: -5.1884
Max Act: 5.0634. Min Act: -0.1700
Data Index: 5040737 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1884. Min Range: -5.1884
Max Act: 5.0947. Min Act: -0.1700
Data Index: 3109260 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1884. Min Range: -5.1884
Max Act: 5.0634. Min Act: -0.1700
Data Index: 5508635 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1884. Min Range: -5.1884
Max Act: 5.0322. Min Act: -0.1700
Data Index: 7461864 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1884. Min Range: -5.1884
Max Act: 5.0322. Min Act: -0.1700
Data Index: 1105386 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1884. Min Range: -5.1884
Max Act: 5.0634. Min Act: -0.1700
Data Index: 3497025 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1884. Min Range: -5.1884
Max Act: 5.0009. Min Act: -0.1700
Data Index: 151437 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1884. Min Range: -5.1884
Max Act: 5.0009. Min Act: -0.1700
Data Index: 7098041 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1884. Min Range: -5.1884
Max Act: 4.9697. Min Act: -0.1700
Data Index: 6844545 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1884. Min Range: -5.1884
Max Act: 4.9697. Min Act: -0.1700
Data Index: 8653930 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1884. Min Range: -5.1884
Max Act: 4.9384. Min Act: -0.1700
Data Index: 5073753 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1884. Min Range: -5.1884
Max Act: 4.9697. Min Act: -0.1700
Data Index: 3045966 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1884. Min Range: -5.1884
Max Act: 4.9697. Min Act: -0.1700
Data Index: 3730535 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1884. Min Range: -5.1884
Max Act: 4.9384. Min Act: -0.1700
Data Index: 1725066 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #19