Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2011 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3249. Min Range: -5.3249
Max Act: 5.3249. Min Act: -0.1700
Data Index: 4772897 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3249. Min Range: -5.3249
Max Act: 5.1062. Min Act: -0.1700
Data Index: 7693436 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3249. Min Range: -5.3249
Max Act: 5.0749. Min Act: -0.1700
Data Index: 626560 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3249. Min Range: -5.3249
Max Act: 5.0749. Min Act: -0.1700
Data Index: 6945548 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3249. Min Range: -5.3249
Max Act: 5.0437. Min Act: -0.1700
Data Index: 5848902 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3249. Min Range: -5.3249
Max Act: 5.0124. Min Act: -0.1700
Data Index: 6977373 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3249. Min Range: -5.3249
Max Act: 5.0437. Min Act: -0.1700
Data Index: 8553628 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3249. Min Range: -5.3249
Max Act: 5.0124. Min Act: -0.1700
Data Index: 2307001 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3249. Min Range: -5.3249
Max Act: 5.0124. Min Act: -0.1700
Data Index: 3084924 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3249. Min Range: -5.3249
Max Act: 4.9812. Min Act: -0.1700
Data Index: 8815763 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3249. Min Range: -5.3249
Max Act: 4.9812. Min Act: -0.1700
Data Index: 1133282 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3249. Min Range: -5.3249
Max Act: 4.9812. Min Act: -0.1700
Data Index: 2920638 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3249. Min Range: -5.3249
Max Act: 4.9499. Min Act: -0.1700
Data Index: 8078275 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3249. Min Range: -5.3249
Max Act: 4.8874. Min Act: -0.1700
Data Index: 626561 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3249. Min Range: -5.3249
Max Act: 4.8874. Min Act: -0.1700
Data Index: 8078273 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3249. Min Range: -5.3249
Max Act: 4.9187. Min Act: -0.1700
Data Index: 5552711 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3249. Min Range: -5.3249
Max Act: 4.9187. Min Act: -0.1700
Data Index: 6004713 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3249. Min Range: -5.3249
Max Act: 4.9187. Min Act: -0.1700
Data Index: 1887267 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3249. Min Range: -5.3249
Max Act: 4.9187. Min Act: -0.1700
Data Index: 5806907 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3249. Min Range: -5.3249
Max Act: 4.9187. Min Act: -0.1700
Data Index: 3577243 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #19