Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4855 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5551. Min Range: -6.5551
Max Act: 6.5551. Min Act: -0.1700
Data Index: 4067548 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5551. Min Range: -6.5551
Max Act: 6.2113. Min Act: -0.1700
Data Index: 6024281 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5551. Min Range: -6.5551
Max Act: 6.1488. Min Act: -0.1700
Data Index: 3439929 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5551. Min Range: -6.5551
Max Act: 6.1488. Min Act: -0.1700
Data Index: 7311861 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5551. Min Range: -6.5551
Max Act: 6.1176. Min Act: -0.1700
Data Index: 3898945 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5551. Min Range: -6.5551
Max Act: 6.1176. Min Act: -0.1700
Data Index: 3988090 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5551. Min Range: -6.5551
Max Act: 6.0551. Min Act: -0.1700
Data Index: 4349877 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5551. Min Range: -6.5551
Max Act: 6.0551. Min Act: -0.1700
Data Index: 2146103 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5551. Min Range: -6.5551
Max Act: 6.0551. Min Act: -0.1700
Data Index: 6078188 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5551. Min Range: -6.5551
Max Act: 6.0551. Min Act: -0.1700
Data Index: 5504622 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5551. Min Range: -6.5551
Max Act: 6.0238. Min Act: -0.1700
Data Index: 6039747 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5551. Min Range: -6.5551
Max Act: 6.0238. Min Act: -0.1700
Data Index: 5167372 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5551. Min Range: -6.5551
Max Act: 5.9613. Min Act: -0.1700
Data Index: 3529878 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5551. Min Range: -6.5551
Max Act: 6.0238. Min Act: -0.1700
Data Index: 647477 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5551. Min Range: -6.5551
Max Act: 5.9926. Min Act: -0.1700
Data Index: 3617538 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5551. Min Range: -6.5551
Max Act: 5.9926. Min Act: -0.1700
Data Index: 8130025 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5551. Min Range: -6.5551
Max Act: 5.9926. Min Act: -0.1700
Data Index: 98417 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5551. Min Range: -6.5551
Max Act: 5.9926. Min Act: -0.1700
Data Index: 4573028 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5551. Min Range: -6.5551
Max Act: 5.9926. Min Act: -0.1700
Data Index: 6154810 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5551. Min Range: -6.5551
Max Act: 5.9926. Min Act: -0.1700
Data Index: 5805767 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #19