Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1978 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1712. Min Range: -5.1712
Max Act: 5.1712. Min Act: -0.1700
Data Index: 4738356 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1712. Min Range: -5.1712
Max Act: 5.1087. Min Act: -0.1700
Data Index: 7033535 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1712. Min Range: -5.1712
Max Act: 5.0774. Min Act: -0.1700
Data Index: 7706066 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1712. Min Range: -5.1712
Max Act: 5.0774. Min Act: -0.1700
Data Index: 890532 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1712. Min Range: -5.1712
Max Act: 5.0462. Min Act: -0.1700
Data Index: 5063814 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1712. Min Range: -5.1712
Max Act: 5.0149. Min Act: -0.1700
Data Index: 2405633 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1712. Min Range: -5.1712
Max Act: 5.0149. Min Act: -0.1700
Data Index: 5207884 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1712. Min Range: -5.1712
Max Act: 4.9837. Min Act: -0.1700
Data Index: 8505403 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1712. Min Range: -5.1712
Max Act: 5.0149. Min Act: -0.1700
Data Index: 6610478 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1712. Min Range: -5.1712
Max Act: 4.9837. Min Act: -0.1700
Data Index: 2008491 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1712. Min Range: -5.1712
Max Act: 4.9524. Min Act: -0.1700
Data Index: 3366256 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1712. Min Range: -5.1712
Max Act: 4.9524. Min Act: -0.1700
Data Index: 7770603 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1712. Min Range: -5.1712
Max Act: 4.8899. Min Act: -0.1700
Data Index: 493105 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1712. Min Range: -5.1712
Max Act: 4.9212. Min Act: -0.1700
Data Index: 2767533 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1712. Min Range: -5.1712
Max Act: 4.9212. Min Act: -0.1700
Data Index: 5634198 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1712. Min Range: -5.1712
Max Act: 4.9212. Min Act: -0.1700
Data Index: 5332038 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1712. Min Range: -5.1712
Max Act: 4.8899. Min Act: -0.1700
Data Index: 942786 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1712. Min Range: -5.1712
Max Act: 4.8899. Min Act: -0.1700
Data Index: 1481318 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1712. Min Range: -5.1712
Max Act: 4.8587. Min Act: -0.1700
Data Index: 1581223 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1712. Min Range: -5.1712
Max Act: 4.8899. Min Act: -0.1700
Data Index: 8112136 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #19