Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2646 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9429. Min Range: -2.9429
Max Act: 2.9429. Min Act: -0.1700
Data Index: 4726298 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9429. Min Range: -2.9429
Max Act: 2.9112. Min Act: -0.1700
Data Index: 8816563 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9429. Min Range: -2.9429
Max Act: 2.9271. Min Act: -0.1700
Data Index: 6506814 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9429. Min Range: -2.9429
Max Act: 2.8954. Min Act: -0.1700
Data Index: 1498535 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9429. Min Range: -2.9429
Max Act: 2.8954. Min Act: -0.1700
Data Index: 1282638 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9429. Min Range: -2.9429
Max Act: 2.8636. Min Act: -0.1700
Data Index: 7193368 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9429. Min Range: -2.9429
Max Act: 2.8636. Min Act: -0.1700
Data Index: 7799917 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9429. Min Range: -2.9429
Max Act: 2.8636. Min Act: -0.1700
Data Index: 7406637 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9429. Min Range: -2.9429
Max Act: 2.8477. Min Act: -0.1700
Data Index: 2200505 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9429. Min Range: -2.9429
Max Act: 2.8477. Min Act: -0.1700
Data Index: 3656053 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9429. Min Range: -2.9429
Max Act: 2.8318. Min Act: -0.1700
Data Index: 6529463 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9429. Min Range: -2.9429
Max Act: 2.8318. Min Act: -0.1700
Data Index: 701595 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9429. Min Range: -2.9429
Max Act: 2.8318. Min Act: -0.1700
Data Index: 8160442 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9429. Min Range: -2.9429
Max Act: 2.8318. Min Act: -0.1700
Data Index: 5846156 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9429. Min Range: -2.9429
Max Act: 2.8318. Min Act: -0.1700
Data Index: 1498537 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9429. Min Range: -2.9429
Max Act: 2.8159. Min Act: -0.1700
Data Index: 667273 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9429. Min Range: -2.9429
Max Act: 2.8000. Min Act: -0.1700
Data Index: 7194 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9429. Min Range: -2.9429
Max Act: 2.8000. Min Act: -0.1700
Data Index: 4232791 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9429. Min Range: -2.9429
Max Act: 2.8000. Min Act: -0.1700
Data Index: 5664003 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9429. Min Range: -2.9429
Max Act: 2.7841. Min Act: -0.1700
Data Index: 7740072 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #19