Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 658 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9653. Min Range: -7.9653
Max Act: 7.9653. Min Act: -0.1700
Data Index: 5525507 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9653. Min Range: -7.9653
Max Act: 7.9340. Min Act: -0.1700
Data Index: 8661659 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9653. Min Range: -7.9653
Max Act: 7.8090. Min Act: -0.1700
Data Index: 3641813 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9653. Min Range: -7.9653
Max Act: 7.7778. Min Act: -0.1700
Data Index: 3053937 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9653. Min Range: -7.9653
Max Act: 7.5903. Min Act: -0.1700
Data Index: 4385838 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9653. Min Range: -7.9653
Max Act: 7.5903. Min Act: -0.1700
Data Index: 6572980 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9653. Min Range: -7.9653
Max Act: 7.4653. Min Act: -0.1700
Data Index: 6808705 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9653. Min Range: -7.9653
Max Act: 7.4340. Min Act: -0.1700
Data Index: 133947 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9653. Min Range: -7.9653
Max Act: 7.2778. Min Act: -0.1700
Data Index: 2140452 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9653. Min Range: -7.9653
Max Act: 7.2778. Min Act: -0.1700
Data Index: 1879594 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9653. Min Range: -7.9653
Max Act: 7.2778. Min Act: -0.1700
Data Index: 5235359 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9653. Min Range: -7.9653
Max Act: 7.2465. Min Act: -0.1700
Data Index: 231660 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9653. Min Range: -7.9653
Max Act: 7.2465. Min Act: -0.1700
Data Index: 1834789 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9653. Min Range: -7.9653
Max Act: 7.2778. Min Act: -0.1700
Data Index: 6314054 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9653. Min Range: -7.9653
Max Act: 7.2153. Min Act: -0.1700
Data Index: 4227310 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9653. Min Range: -7.9653
Max Act: 7.2153. Min Act: -0.1700
Data Index: 1392502 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9653. Min Range: -7.9653
Max Act: 7.2153. Min Act: -0.1700
Data Index: 7035236 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9653. Min Range: -7.9653
Max Act: 7.1840. Min Act: -0.1700
Data Index: 279306 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9653. Min Range: -7.9653
Max Act: 7.2153. Min Act: -0.1700
Data Index: 5486517 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9653. Min Range: -7.9653
Max Act: 7.1840. Min Act: -0.1700
Data Index: 3280329 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #19