Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3104 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1654. Min Range: -6.1654
Max Act: 6.1654. Min Act: -0.1700
Data Index: 8754066 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1654. Min Range: -6.1654
Max Act: 6.1654. Min Act: -0.1700
Data Index: 3077402 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1654. Min Range: -6.1654
Max Act: 6.1029. Min Act: -0.1700
Data Index: 8654779 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1654. Min Range: -6.1654
Max Act: 6.1029. Min Act: -0.1677
Data Index: 253080 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1654. Min Range: -6.1654
Max Act: 6.0716. Min Act: -0.1700
Data Index: 8070445 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1654. Min Range: -6.1654
Max Act: 6.1029. Min Act: -0.1700
Data Index: 7842043 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1654. Min Range: -6.1654
Max Act: 6.0091. Min Act: -0.1700
Data Index: 6399941 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1654. Min Range: -6.1654
Max Act: 6.0091. Min Act: -0.1700
Data Index: 4992842 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1654. Min Range: -6.1654
Max Act: 5.9779. Min Act: -0.1697
Data Index: 7442590 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1654. Min Range: -6.1654
Max Act: 5.9779. Min Act: -0.1700
Data Index: 128990 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1654. Min Range: -6.1654
Max Act: 5.9779. Min Act: -0.1693
Data Index: 900613 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1654. Min Range: -6.1654
Max Act: 5.9779. Min Act: -0.1700
Data Index: 6307049 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1654. Min Range: -6.1654
Max Act: 5.9154. Min Act: -0.1700
Data Index: 4782400 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1654. Min Range: -6.1654
Max Act: 5.9154. Min Act: -0.1700
Data Index: 6307048 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1654. Min Range: -6.1654
Max Act: 5.9154. Min Act: -0.1698
Data Index: 3612380 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1654. Min Range: -6.1654
Max Act: 5.8841. Min Act: -0.1700
Data Index: 2993906 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1654. Min Range: -6.1654
Max Act: 5.8841. Min Act: -0.1699
Data Index: 4744543 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1654. Min Range: -6.1654
Max Act: 5.8529. Min Act: -0.1700
Data Index: 7758128 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1654. Min Range: -6.1654
Max Act: 5.8529. Min Act: -0.1694
Data Index: 6769295 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1654. Min Range: -6.1654
Max Act: 5.8216. Min Act: -0.1700
Data Index: 6962527 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #19