Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3637 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8733. Min Range: -5.8733
Max Act: 5.8733. Min Act: -0.1700
Data Index: 7317908 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8733. Min Range: -5.8733
Max Act: 5.6546. Min Act: -0.1700
Data Index: 2866743 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8733. Min Range: -5.8733
Max Act: 5.6858. Min Act: -0.1700
Data Index: 6702984 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8733. Min Range: -5.8733
Max Act: 5.6546. Min Act: -0.1700
Data Index: 5965769 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8733. Min Range: -5.8733
Max Act: 5.5921. Min Act: -0.1700
Data Index: 5082277 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8733. Min Range: -5.8733
Max Act: 5.5921. Min Act: -0.1700
Data Index: 5765729 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8733. Min Range: -5.8733
Max Act: 5.5921. Min Act: -0.1700
Data Index: 6389151 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8733. Min Range: -5.8733
Max Act: 5.5608. Min Act: -0.1700
Data Index: 5082362 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8733. Min Range: -5.8733
Max Act: 5.5608. Min Act: -0.1700
Data Index: 5339615 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8733. Min Range: -5.8733
Max Act: 5.5296. Min Act: -0.1700
Data Index: 1267873 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8733. Min Range: -5.8733
Max Act: 5.4983. Min Act: -0.1700
Data Index: 3377430 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8733. Min Range: -5.8733
Max Act: 5.4671. Min Act: -0.1700
Data Index: 4711431 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8733. Min Range: -5.8733
Max Act: 5.4671. Min Act: -0.1700
Data Index: 742090 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8733. Min Range: -5.8733
Max Act: 5.4983. Min Act: -0.1700
Data Index: 39962 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8733. Min Range: -5.8733
Max Act: 5.4358. Min Act: -0.1700
Data Index: 3610527 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8733. Min Range: -5.8733
Max Act: 5.4046. Min Act: -0.1700
Data Index: 4671208 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8733. Min Range: -5.8733
Max Act: 5.3733. Min Act: -0.1700
Data Index: 343642 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8733. Min Range: -5.8733
Max Act: 5.3733. Min Act: -0.1700
Data Index: 7035974 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8733. Min Range: -5.8733
Max Act: 5.3733. Min Act: -0.1700
Data Index: 3249431 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8733. Min Range: -5.8733
Max Act: 5.3421. Min Act: -0.1700
Data Index: 5101951 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #19