Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2507 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7600. Min Range: -3.7600
Max Act: 3.7600. Min Act: -0.1700
Data Index: 7714448 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7600. Min Range: -3.7600
Max Act: 3.6661. Min Act: -0.1700
Data Index: 2968386 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7600. Min Range: -3.7600
Max Act: 3.6661. Min Act: -0.1700
Data Index: 6310835 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7600. Min Range: -3.7600
Max Act: 3.6348. Min Act: -0.1700
Data Index: 6150008 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7600. Min Range: -3.7600
Max Act: 3.6348. Min Act: -0.1700
Data Index: 7872046 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7600. Min Range: -3.7600
Max Act: 3.6035. Min Act: -0.1700
Data Index: 1954451 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7600. Min Range: -3.7600
Max Act: 3.6035. Min Act: -0.1700
Data Index: 8067306 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7600. Min Range: -3.7600
Max Act: 3.5722. Min Act: -0.1700
Data Index: 6330855 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7600. Min Range: -3.7600
Max Act: 3.5722. Min Act: -0.1700
Data Index: 1203001 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7600. Min Range: -3.7600
Max Act: 3.5722. Min Act: -0.1700
Data Index: 7791009 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7600. Min Range: -3.7600
Max Act: 3.5722. Min Act: -0.1700
Data Index: 1121968 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7600. Min Range: -3.7600
Max Act: 3.5409. Min Act: -0.1700
Data Index: 1846306 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7600. Min Range: -3.7600
Max Act: 3.5096. Min Act: -0.1700
Data Index: 7387377 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7600. Min Range: -3.7600
Max Act: 3.5722. Min Act: -0.1700
Data Index: 2215747 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7600. Min Range: -3.7600
Max Act: 3.5409. Min Act: -0.1700
Data Index: 675180 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7600. Min Range: -3.7600
Max Act: 3.5409. Min Act: -0.1700
Data Index: 7714447 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7600. Min Range: -3.7600
Max Act: 3.5096. Min Act: -0.1700
Data Index: 3282652 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7600. Min Range: -3.7600
Max Act: 3.5096. Min Act: -0.1700
Data Index: 5235680 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7600. Min Range: -3.7600
Max Act: 3.5096. Min Act: -0.1700
Data Index: 8632917 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7600. Min Range: -3.7600
Max Act: 3.5096. Min Act: -0.1700
Data Index: 320735 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19