Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3935 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7809. Min Range: -5.7809
Max Act: 5.7809. Min Act: -0.1700
Data Index: 8577365 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7809. Min Range: -5.7809
Max Act: 5.4684. Min Act: -0.1700
Data Index: 7530781 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7809. Min Range: -5.7809
Max Act: 5.4059. Min Act: -0.1700
Data Index: 3426463 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7809. Min Range: -5.7809
Max Act: 5.4372. Min Act: -0.1700
Data Index: 916058 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7809. Min Range: -5.7809
Max Act: 5.4684. Min Act: -0.1700
Data Index: 2016962 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7809. Min Range: -5.7809
Max Act: 5.4059. Min Act: -0.1700
Data Index: 923057 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7809. Min Range: -5.7809
Max Act: 5.4059. Min Act: -0.1700
Data Index: 7843397 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7809. Min Range: -5.7809
Max Act: 5.3747. Min Act: -0.1700
Data Index: 503934 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7809. Min Range: -5.7809
Max Act: 5.4059. Min Act: -0.1700
Data Index: 7779618 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7809. Min Range: -5.7809
Max Act: 5.3434. Min Act: -0.1700
Data Index: 472947 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7809. Min Range: -5.7809
Max Act: 5.3434. Min Act: -0.1700
Data Index: 4252925 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7809. Min Range: -5.7809
Max Act: 5.3434. Min Act: -0.1700
Data Index: 2912610 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7809. Min Range: -5.7809
Max Act: 5.3434. Min Act: -0.1700
Data Index: 3674333 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7809. Min Range: -5.7809
Max Act: 5.3122. Min Act: -0.1700
Data Index: 3846407 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7809. Min Range: -5.7809
Max Act: 5.3122. Min Act: -0.1700
Data Index: 1935162 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7809. Min Range: -5.7809
Max Act: 5.2809. Min Act: -0.1700
Data Index: 3681101 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7809. Min Range: -5.7809
Max Act: 5.2809. Min Act: -0.1700
Data Index: 3976263 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7809. Min Range: -5.7809
Max Act: 5.2809. Min Act: -0.1700
Data Index: 2808341 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7809. Min Range: -5.7809
Max Act: 5.2497. Min Act: -0.1700
Data Index: 7728135 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7809. Min Range: -5.7809
Max Act: 5.2809. Min Act: -0.1700
Data Index: 7390072 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #19