Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2952 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5438. Min Range: -9.5438
Max Act: 9.5438. Min Act: -0.1700
Data Index: 6521781 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5438. Min Range: -9.5438
Max Act: 9.4188. Min Act: -0.1700
Data Index: 1243573 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5438. Min Range: -9.5438
Max Act: 9.3563. Min Act: -0.1700
Data Index: 4672873 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5438. Min Range: -9.5438
Max Act: 9.3563. Min Act: -0.1700
Data Index: 5383205 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5438. Min Range: -9.5438
Max Act: 9.3563. Min Act: -0.1700
Data Index: 5887856 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5438. Min Range: -9.5438
Max Act: 9.2938. Min Act: -0.1700
Data Index: 5102128 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5438. Min Range: -9.5438
Max Act: 9.2938. Min Act: -0.1700
Data Index: 5718981 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5438. Min Range: -9.5438
Max Act: 9.2313. Min Act: -0.1700
Data Index: 3754984 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5438. Min Range: -9.5438
Max Act: 9.2313. Min Act: -0.1700
Data Index: 6774738 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5438. Min Range: -9.5438
Max Act: 9.2313. Min Act: -0.1700
Data Index: 8687667 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5438. Min Range: -9.5438
Max Act: 9.1688. Min Act: -0.1700
Data Index: 906644 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5438. Min Range: -9.5438
Max Act: 9.1688. Min Act: -0.1700
Data Index: 7501044 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5438. Min Range: -9.5438
Max Act: 9.1063. Min Act: -0.1700
Data Index: 127642 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5438. Min Range: -9.5438
Max Act: 9.1063. Min Act: -0.1700
Data Index: 291020 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5438. Min Range: -9.5438
Max Act: 9.1063. Min Act: -0.1700
Data Index: 3474487 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5438. Min Range: -9.5438
Max Act: 9.1063. Min Act: -0.1700
Data Index: 1632784 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5438. Min Range: -9.5438
Max Act: 9.0438. Min Act: -0.1700
Data Index: 2587670 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5438. Min Range: -9.5438
Max Act: 9.0438. Min Act: -0.1700
Data Index: 1055083 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5438. Min Range: -9.5438
Max Act: 9.0438. Min Act: -0.1700
Data Index: 4688275 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5438. Min Range: -9.5438
Max Act: 9.0438. Min Act: -0.1700
Data Index: 4528980 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #19