Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3338 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1750. Min Range: -5.1750
Max Act: 5.1750. Min Act: -0.1700
Data Index: 6786865 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1750. Min Range: -5.1750
Max Act: 4.8938. Min Act: -0.1700
Data Index: 5554830 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1750. Min Range: -5.1750
Max Act: 4.7063. Min Act: -0.1700
Data Index: 6835587 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1750. Min Range: -5.1750
Max Act: 4.7063. Min Act: -0.1700
Data Index: 7172265 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1750. Min Range: -5.1750
Max Act: 4.6750. Min Act: -0.1700
Data Index: 3811187 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1750. Min Range: -5.1750
Max Act: 4.6438. Min Act: -0.1700
Data Index: 6033370 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1750. Min Range: -5.1750
Max Act: 4.5500. Min Act: -0.1700
Data Index: 326151 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1750. Min Range: -5.1750
Max Act: 4.5188. Min Act: -0.1700
Data Index: 8408979 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1750. Min Range: -5.1750
Max Act: 4.5500. Min Act: -0.1700
Data Index: 3774936 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1750. Min Range: -5.1750
Max Act: 4.5188. Min Act: -0.1700
Data Index: 370046 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1750. Min Range: -5.1750
Max Act: 4.5188. Min Act: -0.1700
Data Index: 5926837 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1750. Min Range: -5.1750
Max Act: 4.5188. Min Act: -0.1700
Data Index: 6580557 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1750. Min Range: -5.1750
Max Act: 4.4875. Min Act: -0.1700
Data Index: 151615 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1750. Min Range: -5.1750
Max Act: 4.4563. Min Act: -0.1700
Data Index: 2797756 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1750. Min Range: -5.1750
Max Act: 4.4250. Min Act: -0.1700
Data Index: 6341982 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1750. Min Range: -5.1750
Max Act: 4.4250. Min Act: -0.1700
Data Index: 7480643 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1750. Min Range: -5.1750
Max Act: 4.4250. Min Act: -0.1700
Data Index: 5556257 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1750. Min Range: -5.1750
Max Act: 4.4250. Min Act: -0.1700
Data Index: 1761895 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1750. Min Range: -5.1750
Max Act: 4.3938. Min Act: -0.1700
Data Index: 6912815 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1750. Min Range: -5.1750
Max Act: 4.3625. Min Act: -0.1700
Data Index: 7397832 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #19