Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2003 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1608. Min Range: -5.1608
Max Act: 5.1608. Min Act: -0.1700
Data Index: 5763928 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1608. Min Range: -5.1608
Max Act: 5.0983. Min Act: -0.1700
Data Index: 5266504 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1608. Min Range: -5.1608
Max Act: 5.0670. Min Act: -0.1700
Data Index: 2397028 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1608. Min Range: -5.1608
Max Act: 4.9733. Min Act: -0.1700
Data Index: 8222786 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1608. Min Range: -5.1608
Max Act: 4.9733. Min Act: -0.1700
Data Index: 6790222 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1608. Min Range: -5.1608
Max Act: 4.9420. Min Act: -0.1700
Data Index: 4709644 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1608. Min Range: -5.1608
Max Act: 4.9420. Min Act: -0.1700
Data Index: 6429624 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1608. Min Range: -5.1608
Max Act: 4.9108. Min Act: -0.1700
Data Index: 324794 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1608. Min Range: -5.1608
Max Act: 4.9108. Min Act: -0.1700
Data Index: 1315600 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1608. Min Range: -5.1608
Max Act: 4.9108. Min Act: -0.1700
Data Index: 219256 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1608. Min Range: -5.1608
Max Act: 4.8795. Min Act: -0.1700
Data Index: 5907964 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1608. Min Range: -5.1608
Max Act: 4.8795. Min Act: -0.1700
Data Index: 4454865 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1608. Min Range: -5.1608
Max Act: 4.8483. Min Act: -0.1700
Data Index: 8470247 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1608. Min Range: -5.1608
Max Act: 4.8795. Min Act: -0.1700
Data Index: 8795555 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1608. Min Range: -5.1608
Max Act: 4.8483. Min Act: -0.1700
Data Index: 4128494 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1608. Min Range: -5.1608
Max Act: 4.8483. Min Act: -0.1700
Data Index: 2961188 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1608. Min Range: -5.1608
Max Act: 4.8170. Min Act: -0.1700
Data Index: 5849151 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1608. Min Range: -5.1608
Max Act: 4.8483. Min Act: -0.1700
Data Index: 1427531 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1608. Min Range: -5.1608
Max Act: 4.7858. Min Act: -0.1700
Data Index: 2981807 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1608. Min Range: -5.1608
Max Act: 4.7858. Min Act: -0.1700
Data Index: 5907965 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #19