Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3821 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0150. Min Range: -5.0150
Max Act: 5.0150. Min Act: -0.1700
Data Index: 3550092 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0150. Min Range: -5.0150
Max Act: 4.7650. Min Act: -0.1700
Data Index: 4885512 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0150. Min Range: -5.0150
Max Act: 4.7337. Min Act: -0.1700
Data Index: 8354659 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0150. Min Range: -5.0150
Max Act: 4.7025. Min Act: -0.1700
Data Index: 4288284 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0150. Min Range: -5.0150
Max Act: 4.6712. Min Act: -0.1700
Data Index: 5376107 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0150. Min Range: -5.0150
Max Act: 4.6087. Min Act: -0.1700
Data Index: 8297588 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0150. Min Range: -5.0150
Max Act: 4.6400. Min Act: -0.1700
Data Index: 460546 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0150. Min Range: -5.0150
Max Act: 4.6087. Min Act: -0.1700
Data Index: 8199108 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0150. Min Range: -5.0150
Max Act: 4.6400. Min Act: -0.1700
Data Index: 7127516 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0150. Min Range: -5.0150
Max Act: 4.6400. Min Act: -0.1700
Data Index: 7924869 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0150. Min Range: -5.0150
Max Act: 4.6400. Min Act: -0.1700
Data Index: 3309638 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0150. Min Range: -5.0150
Max Act: 4.6087. Min Act: -0.1700
Data Index: 7237146 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0150. Min Range: -5.0150
Max Act: 4.5775. Min Act: -0.1700
Data Index: 8571777 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0150. Min Range: -5.0150
Max Act: 4.6087. Min Act: -0.1700
Data Index: 2980875 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0150. Min Range: -5.0150
Max Act: 4.6087. Min Act: -0.1700
Data Index: 4133922 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0150. Min Range: -5.0150
Max Act: 4.5775. Min Act: -0.1700
Data Index: 5593653 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0150. Min Range: -5.0150
Max Act: 4.5775. Min Act: -0.1700
Data Index: 7519932 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0150. Min Range: -5.0150
Max Act: 4.5775. Min Act: -0.1700
Data Index: 8571785 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0150. Min Range: -5.0150
Max Act: 4.5462. Min Act: -0.1700
Data Index: 1920445 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0150. Min Range: -5.0150
Max Act: 4.5462. Min Act: -0.1700
Data Index: 103422 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #19