Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1655 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4475. Min Range: -6.4475
Max Act: 6.4475. Min Act: -0.1700
Data Index: 1369238 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4475. Min Range: -6.4475
Max Act: 6.1038. Min Act: -0.1700
Data Index: 2872794 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4475. Min Range: -6.4475
Max Act: 6.0725. Min Act: -0.1700
Data Index: 3306135 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4475. Min Range: -6.4475
Max Act: 6.0725. Min Act: -0.1700
Data Index: 7049479 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4475. Min Range: -6.4475
Max Act: 6.0413. Min Act: -0.1700
Data Index: 3973699 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4475. Min Range: -6.4475
Max Act: 6.0413. Min Act: -0.1700
Data Index: 1673759 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4475. Min Range: -6.4475
Max Act: 6.0100. Min Act: -0.1700
Data Index: 1632412 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4475. Min Range: -6.4475
Max Act: 5.9788. Min Act: -0.1700
Data Index: 1861642 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4475. Min Range: -6.4475
Max Act: 5.8538. Min Act: -0.1700
Data Index: 6153620 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4475. Min Range: -6.4475
Max Act: 5.7913. Min Act: -0.1700
Data Index: 7448512 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4475. Min Range: -6.4475
Max Act: 5.7600. Min Act: -0.1700
Data Index: 5808084 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4475. Min Range: -6.4475
Max Act: 5.7600. Min Act: -0.1700
Data Index: 2190327 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4475. Min Range: -6.4475
Max Act: 5.7600. Min Act: -0.1700
Data Index: 3582007 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4475. Min Range: -6.4475
Max Act: 5.7600. Min Act: -0.1700
Data Index: 2529435 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4475. Min Range: -6.4475
Max Act: 5.7600. Min Act: -0.1700
Data Index: 5112962 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4475. Min Range: -6.4475
Max Act: 5.7600. Min Act: -0.1700
Data Index: 4923777 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4475. Min Range: -6.4475
Max Act: 5.7600. Min Act: -0.1700
Data Index: 2748391 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4475. Min Range: -6.4475
Max Act: 5.7288. Min Act: -0.1700
Data Index: 2963675 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4475. Min Range: -6.4475
Max Act: 5.7288. Min Act: -0.1700
Data Index: 2775814 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4475. Min Range: -6.4475
Max Act: 5.7288. Min Act: -0.1700
Data Index: 6517379 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #19