Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3805 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9442. Min Range: -4.9442
Max Act: 4.9442. Min Act: -0.1700
Data Index: 1898974 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9442. Min Range: -4.9442
Max Act: 4.7255. Min Act: -0.1700
Data Index: 6646816 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9442. Min Range: -4.9442
Max Act: 4.6630. Min Act: -0.1700
Data Index: 2865629 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9442. Min Range: -4.9442
Max Act: 4.5692. Min Act: -0.1700
Data Index: 8329752 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9442. Min Range: -4.9442
Max Act: 4.4442. Min Act: -0.1700
Data Index: 1898975 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9442. Min Range: -4.9442
Max Act: 4.4442. Min Act: -0.1700
Data Index: 4606100 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9442. Min Range: -4.9442
Max Act: 4.4130. Min Act: -0.1700
Data Index: 564271 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9442. Min Range: -4.9442
Max Act: 4.4130. Min Act: -0.1700
Data Index: 1506373 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9442. Min Range: -4.9442
Max Act: 4.4130. Min Act: -0.1700
Data Index: 6549785 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9442. Min Range: -4.9442
Max Act: 4.3505. Min Act: -0.1700
Data Index: 6246951 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9442. Min Range: -4.9442
Max Act: 4.4130. Min Act: -0.1700
Data Index: 4056669 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9442. Min Range: -4.9442
Max Act: 4.3817. Min Act: -0.1700
Data Index: 2620295 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9442. Min Range: -4.9442
Max Act: 4.3817. Min Act: -0.1700
Data Index: 5568078 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9442. Min Range: -4.9442
Max Act: 4.3505. Min Act: -0.1700
Data Index: 6720109 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9442. Min Range: -4.9442
Max Act: 4.3505. Min Act: -0.1700
Data Index: 7813345 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9442. Min Range: -4.9442
Max Act: 4.3192. Min Act: -0.1700
Data Index: 6704520 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9442. Min Range: -4.9442
Max Act: 4.3192. Min Act: -0.1700
Data Index: 551565 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9442. Min Range: -4.9442
Max Act: 4.3505. Min Act: -0.1700
Data Index: 8024681 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9442. Min Range: -4.9442
Max Act: 4.2880. Min Act: -0.1700
Data Index: 6466695 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9442. Min Range: -4.9442
Max Act: 4.2880. Min Act: -0.1700
Data Index: 315668 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #19