Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3567 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.8126. Min Act: -0.1700
Data Index: 786693 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.4689. Min Act: -0.1700
Data Index: 5963235 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.4689. Min Act: -0.1700
Data Index: 6584855 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.4064. Min Act: -0.1700
Data Index: 228262 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.3751. Min Act: -0.1700
Data Index: 4749221 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.3751. Min Act: -0.1700
Data Index: 6881952 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.3439. Min Act: -0.1700
Data Index: 6166537 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.2814. Min Act: -0.1700
Data Index: 5214398 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.3126. Min Act: -0.1700
Data Index: 1507037 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.2501. Min Act: -0.1700
Data Index: 5814522 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.2189. Min Act: -0.1700
Data Index: 3111231 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.1876. Min Act: -0.1700
Data Index: 4496905 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.1876. Min Act: -0.1700
Data Index: 8183406 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.1876. Min Act: -0.1700
Data Index: 2807706 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.1564. Min Act: -0.1700
Data Index: 405948 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.1251. Min Act: -0.1700
Data Index: 7143532 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.1251. Min Act: -0.1700
Data Index: 2984886 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.0939. Min Act: -0.1700
Data Index: 119956 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.0939. Min Act: -0.1700
Data Index: 5683391 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.0626. Min Act: -0.1700
Data Index: 3993511 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #19