Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4966 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1331. Min Range: -5.1331
Max Act: 5.1331. Min Act: -0.1700
Data Index: 1271580 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1331. Min Range: -5.1331
Max Act: 5.0706. Min Act: -0.1700
Data Index: 3903600 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1331. Min Range: -5.1331
Max Act: 5.1018. Min Act: -0.1700
Data Index: 6544879 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1331. Min Range: -5.1331
Max Act: 5.0706. Min Act: -0.1700
Data Index: 2018836 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1331. Min Range: -5.1331
Max Act: 5.0393. Min Act: -0.1700
Data Index: 1804077 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1331. Min Range: -5.1331
Max Act: 5.0081. Min Act: -0.1700
Data Index: 2775283 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1331. Min Range: -5.1331
Max Act: 5.0081. Min Act: -0.1700
Data Index: 5329723 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1331. Min Range: -5.1331
Max Act: 5.0081. Min Act: -0.1700
Data Index: 7614356 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1331. Min Range: -5.1331
Max Act: 4.9456. Min Act: -0.1700
Data Index: 7238286 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1331. Min Range: -5.1331
Max Act: 4.9456. Min Act: -0.1700
Data Index: 7210513 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1331. Min Range: -5.1331
Max Act: 4.9456. Min Act: -0.1700
Data Index: 7789655 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1331. Min Range: -5.1331
Max Act: 4.9456. Min Act: -0.1700
Data Index: 8132470 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1331. Min Range: -5.1331
Max Act: 4.9456. Min Act: -0.1700
Data Index: 8615722 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1331. Min Range: -5.1331
Max Act: 4.9143. Min Act: -0.1700
Data Index: 3477241 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1331. Min Range: -5.1331
Max Act: 4.9143. Min Act: -0.1700
Data Index: 943318 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1331. Min Range: -5.1331
Max Act: 4.9143. Min Act: -0.1700
Data Index: 8110561 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1331. Min Range: -5.1331
Max Act: 4.9143. Min Act: -0.1700
Data Index: 7099246 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1331. Min Range: -5.1331
Max Act: 4.9143. Min Act: -0.1700
Data Index: 1995148 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1331. Min Range: -5.1331
Max Act: 4.8831. Min Act: -0.1700
Data Index: 3381877 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1331. Min Range: -5.1331
Max Act: 4.8831. Min Act: -0.1700
Data Index: 6917624 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19