Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 191 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9066. Min Range: -9.9066
Max Act: 9.9066. Min Act: -0.1700
Data Index: 4657660 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9066. Min Range: -9.9066
Max Act: 9.4066. Min Act: -0.1700
Data Index: 1940711 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9066. Min Range: -9.9066
Max Act: 9.0941. Min Act: -0.1700
Data Index: 2422674 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9066. Min Range: -9.9066
Max Act: 9.0316. Min Act: -0.1700
Data Index: 7211790 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9066. Min Range: -9.9066
Max Act: 8.9691. Min Act: -0.1700
Data Index: 2283428 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9066. Min Range: -9.9066
Max Act: 8.9691. Min Act: -0.1700
Data Index: 3625673 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9066. Min Range: -9.9066
Max Act: 8.9691. Min Act: -0.1700
Data Index: 5469547 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9066. Min Range: -9.9066
Max Act: 8.9066. Min Act: -0.1700
Data Index: 8625276 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9066. Min Range: -9.9066
Max Act: 8.8441. Min Act: -0.1700
Data Index: 4338346 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9066. Min Range: -9.9066
Max Act: 8.7816. Min Act: -0.1700
Data Index: 8733984 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9066. Min Range: -9.9066
Max Act: 8.7191. Min Act: -0.1700
Data Index: 4539700 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9066. Min Range: -9.9066
Max Act: 8.7191. Min Act: -0.1700
Data Index: 8302798 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9066. Min Range: -9.9066
Max Act: 8.7191. Min Act: -0.1700
Data Index: 7596884 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9066. Min Range: -9.9066
Max Act: 8.6566. Min Act: -0.1700
Data Index: 5170586 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9066. Min Range: -9.9066
Max Act: 8.6566. Min Act: -0.1700
Data Index: 5521345 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9066. Min Range: -9.9066
Max Act: 8.6566. Min Act: -0.1700
Data Index: 6929698 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9066. Min Range: -9.9066
Max Act: 8.6566. Min Act: -0.1700
Data Index: 7826600 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9066. Min Range: -9.9066
Max Act: 8.6566. Min Act: -0.1700
Data Index: 3742047 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9066. Min Range: -9.9066
Max Act: 8.6566. Min Act: -0.1700
Data Index: 8229475 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9066. Min Range: -9.9066
Max Act: 8.5941. Min Act: -0.1700
Data Index: 6896331 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19