Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4735 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4155. Min Range: -7.4155
Max Act: 7.4155. Min Act: -0.1700
Data Index: 1285922 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4155. Min Range: -7.4155
Max Act: 7.4155. Min Act: -0.1700
Data Index: 8303748 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4155. Min Range: -7.4155
Max Act: 7.3217. Min Act: -0.1700
Data Index: 2699187 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4155. Min Range: -7.4155
Max Act: 7.2280. Min Act: -0.1700
Data Index: 8294083 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4155. Min Range: -7.4155
Max Act: 7.1967. Min Act: -0.1700
Data Index: 1232519 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4155. Min Range: -7.4155
Max Act: 7.1655. Min Act: -0.1700
Data Index: 7801549 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4155. Min Range: -7.4155
Max Act: 7.1342. Min Act: -0.1700
Data Index: 5719452 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4155. Min Range: -7.4155
Max Act: 7.1342. Min Act: -0.1700
Data Index: 4332227 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4155. Min Range: -7.4155
Max Act: 7.0717. Min Act: -0.1700
Data Index: 1789600 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4155. Min Range: -7.4155
Max Act: 7.1030. Min Act: -0.1700
Data Index: 4483811 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4155. Min Range: -7.4155
Max Act: 7.0405. Min Act: -0.1700
Data Index: 769724 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4155. Min Range: -7.4155
Max Act: 7.0405. Min Act: -0.1700
Data Index: 4099930 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4155. Min Range: -7.4155
Max Act: 7.0092. Min Act: -0.1700
Data Index: 5997524 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4155. Min Range: -7.4155
Max Act: 6.9467. Min Act: -0.1700
Data Index: 4654588 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4155. Min Range: -7.4155
Max Act: 6.9467. Min Act: -0.1700
Data Index: 2687235 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4155. Min Range: -7.4155
Max Act: 6.9467. Min Act: -0.1700
Data Index: 1828180 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4155. Min Range: -7.4155
Max Act: 6.9155. Min Act: -0.1700
Data Index: 3336182 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4155. Min Range: -7.4155
Max Act: 6.9155. Min Act: -0.1700
Data Index: 5915364 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4155. Min Range: -7.4155
Max Act: 6.8842. Min Act: -0.1700
Data Index: 8626840 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4155. Min Range: -7.4155
Max Act: 6.9155. Min Act: -0.1700
Data Index: 6073635 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #19