Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2671 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2748. Min Range: -6.2748
Max Act: 6.2748. Min Act: -0.1700
Data Index: 5771634 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2748. Min Range: -6.2748
Max Act: 6.0248. Min Act: -0.1700
Data Index: 6613418 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2748. Min Range: -6.2748
Max Act: 5.8686. Min Act: -0.1700
Data Index: 5372220 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2748. Min Range: -6.2748
Max Act: 5.7748. Min Act: -0.1700
Data Index: 4724907 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2748. Min Range: -6.2748
Max Act: 5.7123. Min Act: -0.1700
Data Index: 7915802 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2748. Min Range: -6.2748
Max Act: 5.6811. Min Act: -0.1700
Data Index: 432594 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2748. Min Range: -6.2748
Max Act: 5.6811. Min Act: -0.1700
Data Index: 2155696 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2748. Min Range: -6.2748
Max Act: 5.6498. Min Act: -0.1700
Data Index: 276547 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2748. Min Range: -6.2748
Max Act: 5.5873. Min Act: -0.1700
Data Index: 1325539 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2748. Min Range: -6.2748
Max Act: 5.5873. Min Act: -0.1700
Data Index: 943728 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2748. Min Range: -6.2748
Max Act: 5.5561. Min Act: -0.1700
Data Index: 6677704 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2748. Min Range: -6.2748
Max Act: 5.5248. Min Act: -0.1700
Data Index: 342357 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2748. Min Range: -6.2748
Max Act: 5.5248. Min Act: -0.1700
Data Index: 3860073 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2748. Min Range: -6.2748
Max Act: 5.4936. Min Act: -0.1700
Data Index: 7628343 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2748. Min Range: -6.2748
Max Act: 5.5248. Min Act: -0.1700
Data Index: 2075879 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2748. Min Range: -6.2748
Max Act: 5.5248. Min Act: -0.1700
Data Index: 1965788 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2748. Min Range: -6.2748
Max Act: 5.4936. Min Act: -0.1700
Data Index: 7640406 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2748. Min Range: -6.2748
Max Act: 5.4936. Min Act: -0.1700
Data Index: 2724251 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2748. Min Range: -6.2748
Max Act: 5.5248. Min Act: -0.1700
Data Index: 4445925 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2748. Min Range: -6.2748
Max Act: 5.4936. Min Act: -0.1700
Data Index: 7996246 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #19