Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5049 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2399. Min Range: -3.2399
Max Act: 3.2399. Min Act: -0.1700
Data Index: 7251905 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2399. Min Range: -3.2399
Max Act: 3.2085. Min Act: -0.1700
Data Index: 2508727 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2399. Min Range: -3.2399
Max Act: 3.2085. Min Act: -0.1700
Data Index: 2459770 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2399. Min Range: -3.2399
Max Act: 3.2085. Min Act: -0.1700
Data Index: 8080071 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2399. Min Range: -3.2399
Max Act: 3.1770. Min Act: -0.1700
Data Index: 2857298 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2399. Min Range: -3.2399
Max Act: 3.1770. Min Act: -0.1700
Data Index: 3846914 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2399. Min Range: -3.2399
Max Act: 3.1770. Min Act: -0.1700
Data Index: 3804201 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2399. Min Range: -3.2399
Max Act: 3.1770. Min Act: -0.1700
Data Index: 3249352 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2399. Min Range: -3.2399
Max Act: 3.1770. Min Act: -0.1700
Data Index: 7014585 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2399. Min Range: -3.2399
Max Act: 3.1770. Min Act: -0.1700
Data Index: 3177124 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2399. Min Range: -3.2399
Max Act: 3.1770. Min Act: -0.1700
Data Index: 6294053 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2399. Min Range: -3.2399
Max Act: 3.1455. Min Act: -0.1700
Data Index: 929393 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2399. Min Range: -3.2399
Max Act: 3.1455. Min Act: -0.1700
Data Index: 1814608 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2399. Min Range: -3.2399
Max Act: 3.1455. Min Act: -0.1700
Data Index: 3865004 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2399. Min Range: -3.2399
Max Act: 3.1455. Min Act: -0.1700
Data Index: 1057629 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2399. Min Range: -3.2399
Max Act: 3.1455. Min Act: -0.1700
Data Index: 4336811 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2399. Min Range: -3.2399
Max Act: 3.1455. Min Act: -0.1700
Data Index: 5131034 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2399. Min Range: -3.2399
Max Act: 3.1455. Min Act: -0.1700
Data Index: 5409418 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2399. Min Range: -3.2399
Max Act: 3.1455. Min Act: -0.1700
Data Index: 271703 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2399. Min Range: -3.2399
Max Act: 3.1140. Min Act: -0.1700
Data Index: 5984987 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #19