Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1993 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0875. Min Range: -3.0875
Max Act: 3.0875. Min Act: -0.1700
Data Index: 6847698 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0875. Min Range: -3.0875
Max Act: 3.0401. Min Act: -0.1700
Data Index: 4174385 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0875. Min Range: -3.0875
Max Act: 3.0086. Min Act: -0.1700
Data Index: 8385463 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0875. Min Range: -3.0875
Max Act: 2.9769. Min Act: -0.1700
Data Index: 7987488 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0875. Min Range: -3.0875
Max Act: 2.9611. Min Act: -0.1700
Data Index: 8741615 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0875. Min Range: -3.0875
Max Act: 2.9453. Min Act: -0.1700
Data Index: 8692235 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0875. Min Range: -3.0875
Max Act: 2.9295. Min Act: -0.1700
Data Index: 4318850 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0875. Min Range: -3.0875
Max Act: 2.9453. Min Act: -0.1700
Data Index: 8556501 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0875. Min Range: -3.0875
Max Act: 2.9453. Min Act: -0.1700
Data Index: 6921718 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0875. Min Range: -3.0875
Max Act: 2.9295. Min Act: -0.1700
Data Index: 2284502 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0875. Min Range: -3.0875
Max Act: 2.9136. Min Act: -0.1700
Data Index: 696968 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0875. Min Range: -3.0875
Max Act: 2.8978. Min Act: -0.1700
Data Index: 160147 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0875. Min Range: -3.0875
Max Act: 2.9136. Min Act: -0.1700
Data Index: 7794573 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0875. Min Range: -3.0875
Max Act: 2.8660. Min Act: -0.1700
Data Index: 60342 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0875. Min Range: -3.0875
Max Act: 2.8819. Min Act: -0.1700
Data Index: 5900166 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0875. Min Range: -3.0875
Max Act: 2.8660. Min Act: -0.1700
Data Index: 3121091 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0875. Min Range: -3.0875
Max Act: 2.8501. Min Act: -0.1700
Data Index: 1777062 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0875. Min Range: -3.0875
Max Act: 2.8501. Min Act: -0.1700
Data Index: 6579140 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0875. Min Range: -3.0875
Max Act: 2.8501. Min Act: -0.1700
Data Index: 6570407 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0875. Min Range: -3.0875
Max Act: 2.8501. Min Act: -0.1700
Data Index: 1477546 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #19