Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1025 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6597. Min Range: -6.6597
Max Act: 6.6597. Min Act: -0.1700
Data Index: 3115631 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6597. Min Range: -6.6597
Max Act: 6.5660. Min Act: -0.1700
Data Index: 457890 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6597. Min Range: -6.6597
Max Act: 6.3160. Min Act: -0.1700
Data Index: 4091469 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6597. Min Range: -6.6597
Max Act: 6.2847. Min Act: -0.1700
Data Index: 6553213 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6597. Min Range: -6.6597
Max Act: 6.1910. Min Act: -0.1700
Data Index: 2647367 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6597. Min Range: -6.6597
Max Act: 6.1597. Min Act: -0.1700
Data Index: 8467906 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6597. Min Range: -6.6597
Max Act: 6.1285. Min Act: -0.1700
Data Index: 1008544 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6597. Min Range: -6.6597
Max Act: 6.0972. Min Act: -0.1700
Data Index: 2005105 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6597. Min Range: -6.6597
Max Act: 6.0972. Min Act: -0.1700
Data Index: 3676073 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6597. Min Range: -6.6597
Max Act: 6.0660. Min Act: -0.1700
Data Index: 6250622 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6597. Min Range: -6.6597
Max Act: 6.0660. Min Act: -0.1700
Data Index: 2247878 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6597. Min Range: -6.6597
Max Act: 6.0660. Min Act: -0.1700
Data Index: 1988488 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6597. Min Range: -6.6597
Max Act: 6.0660. Min Act: -0.1700
Data Index: 5190643 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6597. Min Range: -6.6597
Max Act: 6.0660. Min Act: -0.1700
Data Index: 5149948 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6597. Min Range: -6.6597
Max Act: 6.0035. Min Act: -0.1700
Data Index: 3297784 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6597. Min Range: -6.6597
Max Act: 6.0035. Min Act: -0.1700
Data Index: 3907435 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6597. Min Range: -6.6597
Max Act: 6.0035. Min Act: -0.1700
Data Index: 5556299 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6597. Min Range: -6.6597
Max Act: 5.9722. Min Act: -0.1700
Data Index: 1099195 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6597. Min Range: -6.6597
Max Act: 5.9722. Min Act: -0.1700
Data Index: 5622244 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6597. Min Range: -6.6597
Max Act: 5.9722. Min Act: -0.1700
Data Index: 1988490 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19