Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2087 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.5106. Min Act: -0.1700
Data Index: 7919442 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.5106. Min Act: -0.1700
Data Index: 993614 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.5106. Min Act: -0.1700
Data Index: 5999560 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.5106. Min Act: -0.1700
Data Index: 4574523 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.4481. Min Act: -0.1700
Data Index: 5081880 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.4481. Min Act: -0.1700
Data Index: 4767847 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.4481. Min Act: -0.1700
Data Index: 3179841 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.4481. Min Act: -0.1700
Data Index: 1551120 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.4481. Min Act: -0.1700
Data Index: 5969179 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.4481. Min Act: -0.1700
Data Index: 6089923 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.4481. Min Act: -0.1700
Data Index: 3973261 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.4794. Min Act: -0.1700
Data Index: 2191996 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.4169. Min Act: -0.1700
Data Index: 4823551 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.3856. Min Act: -0.1700
Data Index: 131896 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.3856. Min Act: -0.1700
Data Index: 8400859 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.3856. Min Act: -0.1700
Data Index: 5764708 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.3856. Min Act: -0.1700
Data Index: 1471813 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.3544. Min Act: -0.1700
Data Index: 5414249 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.3544. Min Act: -0.1700
Data Index: 2900610 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.3544. Min Act: -0.1700
Data Index: 3834512 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #19