Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6032 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.8881. Min Act: -0.1700
Data Index: 7868257 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.8568. Min Act: -0.1700
Data Index: 2569798 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.8568. Min Act: -0.1700
Data Index: 4176688 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.8568. Min Act: -0.1700
Data Index: 4650614 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.7318. Min Act: -0.1700
Data Index: 6100802 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.7318. Min Act: -0.1700
Data Index: 8321510 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.7318. Min Act: -0.1700
Data Index: 8681097 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.6693. Min Act: -0.1700
Data Index: 26424 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.6693. Min Act: -0.1700
Data Index: 6576660 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.6693. Min Act: -0.1700
Data Index: 5205554 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.6381. Min Act: -0.1700
Data Index: 389569 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.6068. Min Act: -0.1700
Data Index: 4487812 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.5756. Min Act: -0.1700
Data Index: 2944994 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.5756. Min Act: -0.1700
Data Index: 6565920 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.5443. Min Act: -0.1700
Data Index: 6491896 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.5756. Min Act: -0.1700
Data Index: 1665367 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.5756. Min Act: -0.1700
Data Index: 2111961 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.5443. Min Act: -0.1700
Data Index: 8661839 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.5443. Min Act: -0.1700
Data Index: 4693929 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.5131. Min Act: -0.1700
Data Index: 6576659 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #19