Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6165 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.4667. Min Act: -0.1700
Data Index: 3362187 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.4042. Min Act: -0.1700
Data Index: 1721480 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.3417. Min Act: -0.1700
Data Index: 1257590 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.2792. Min Act: -0.1700
Data Index: 6511492 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.1854. Min Act: -0.1700
Data Index: 1244858 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.2167. Min Act: -0.1700
Data Index: 1810930 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.1854. Min Act: -0.1700
Data Index: 4908886 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.1854. Min Act: -0.1700
Data Index: 613952 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.1854. Min Act: -0.1700
Data Index: 8209990 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.1542. Min Act: -0.1700
Data Index: 4010428 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.1229. Min Act: -0.1700
Data Index: 4882513 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.1229. Min Act: -0.1700
Data Index: 172952 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.1229. Min Act: -0.1700
Data Index: 3241711 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.1229. Min Act: -0.1700
Data Index: 4490818 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.1229. Min Act: -0.1700
Data Index: 396795 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.1229. Min Act: -0.1700
Data Index: 137735 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.1229. Min Act: -0.1700
Data Index: 3531968 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.1229. Min Act: -0.1700
Data Index: 3649186 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.1229. Min Act: -0.1700
Data Index: 3658183 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.1229. Min Act: -0.1700
Data Index: 4177193 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19