Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2573 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9928. Min Range: -6.9928
Max Act: 6.9928. Min Act: -0.1700
Data Index: 5044462 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9928. Min Range: -6.9928
Max Act: 6.9615. Min Act: -0.1700
Data Index: 6505941 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9928. Min Range: -6.9928
Max Act: 6.8990. Min Act: -0.1700
Data Index: 2830668 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9928. Min Range: -6.9928
Max Act: 6.8365. Min Act: -0.1700
Data Index: 5722939 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9928. Min Range: -6.9928
Max Act: 6.8365. Min Act: -0.1700
Data Index: 4970808 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9928. Min Range: -6.9928
Max Act: 6.8053. Min Act: -0.1700
Data Index: 7774806 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9928. Min Range: -6.9928
Max Act: 6.7740. Min Act: -0.1700
Data Index: 6716862 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9928. Min Range: -6.9928
Max Act: 6.7428. Min Act: -0.1700
Data Index: 2857362 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9928. Min Range: -6.9928
Max Act: 6.7428. Min Act: -0.1700
Data Index: 6360386 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9928. Min Range: -6.9928
Max Act: 6.7115. Min Act: -0.1700
Data Index: 3835600 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9928. Min Range: -6.9928
Max Act: 6.6803. Min Act: -0.1700
Data Index: 7940949 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9928. Min Range: -6.9928
Max Act: 6.6490. Min Act: -0.1700
Data Index: 6375929 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9928. Min Range: -6.9928
Max Act: 6.6803. Min Act: -0.1700
Data Index: 193533 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9928. Min Range: -6.9928
Max Act: 6.6803. Min Act: -0.1700
Data Index: 141994 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9928. Min Range: -6.9928
Max Act: 6.6490. Min Act: -0.1700
Data Index: 3538710 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9928. Min Range: -6.9928
Max Act: 6.6490. Min Act: -0.1700
Data Index: 6646619 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9928. Min Range: -6.9928
Max Act: 6.6490. Min Act: -0.1700
Data Index: 6183091 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9928. Min Range: -6.9928
Max Act: 6.6490. Min Act: -0.1700
Data Index: 1567301 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9928. Min Range: -6.9928
Max Act: 6.6178. Min Act: -0.1700
Data Index: 5194886 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9928. Min Range: -6.9928
Max Act: 6.5865. Min Act: -0.1700
Data Index: 4741651 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #19