Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1986 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2458. Min Range: -5.2458
Max Act: 5.2458. Min Act: -0.1700
Data Index: 2707466 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2458. Min Range: -5.2458
Max Act: 5.2458. Min Act: -0.1700
Data Index: 6886983 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2458. Min Range: -5.2458
Max Act: 5.2458. Min Act: -0.1700
Data Index: 105041 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2458. Min Range: -5.2458
Max Act: 5.2458. Min Act: -0.1698
Data Index: 1402469 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2458. Min Range: -5.2458
Max Act: 5.2458. Min Act: -0.1700
Data Index: 7871107 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2458. Min Range: -5.2458
Max Act: 5.2145. Min Act: -0.1700
Data Index: 8549994 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2458. Min Range: -5.2458
Max Act: 5.1833. Min Act: -0.1700
Data Index: 8267566 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2458. Min Range: -5.2458
Max Act: 5.1833. Min Act: -0.1700
Data Index: 2533206 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2458. Min Range: -5.2458
Max Act: 5.1833. Min Act: -0.1700
Data Index: 1157759 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2458. Min Range: -5.2458
Max Act: 5.1520. Min Act: -0.1700
Data Index: 8361314 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2458. Min Range: -5.2458
Max Act: 5.1520. Min Act: -0.1700
Data Index: 4878504 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2458. Min Range: -5.2458
Max Act: 5.1520. Min Act: -0.1700
Data Index: 557547 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2458. Min Range: -5.2458
Max Act: 5.1520. Min Act: -0.1700
Data Index: 3618214 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2458. Min Range: -5.2458
Max Act: 5.1520. Min Act: -0.1700
Data Index: 4537662 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2458. Min Range: -5.2458
Max Act: 5.1520. Min Act: -0.1700
Data Index: 3732816 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2458. Min Range: -5.2458
Max Act: 5.1520. Min Act: -0.1700
Data Index: 123657 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2458. Min Range: -5.2458
Max Act: 5.1520. Min Act: -0.1693
Data Index: 7305636 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2458. Min Range: -5.2458
Max Act: 5.0895. Min Act: -0.1700
Data Index: 6716024 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2458. Min Range: -5.2458
Max Act: 5.1208. Min Act: -0.1700
Data Index: 6797927 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2458. Min Range: -5.2458
Max Act: 5.1208. Min Act: -0.1700
Data Index: 3736980 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #19