Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1657 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7565. Min Range: -2.7565
Max Act: 2.7565. Min Act: -0.1700
Data Index: 1697300 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7565. Min Range: -2.7565
Max Act: 2.7086. Min Act: -0.1700
Data Index: 2801729 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7565. Min Range: -2.7565
Max Act: 2.7245. Min Act: -0.1700
Data Index: 6698227 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7565. Min Range: -2.7565
Max Act: 2.7245. Min Act: -0.1700
Data Index: 4464644 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7565. Min Range: -2.7565
Max Act: 2.7086. Min Act: -0.1700
Data Index: 6198067 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7565. Min Range: -2.7565
Max Act: 2.7245. Min Act: -0.1700
Data Index: 1791494 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7565. Min Range: -2.7565
Max Act: 2.7086. Min Act: -0.1700
Data Index: 7525566 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7565. Min Range: -2.7565
Max Act: 2.6765. Min Act: -0.1700
Data Index: 2672536 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7565. Min Range: -2.7565
Max Act: 2.6925. Min Act: -0.1700
Data Index: 1695870 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7565. Min Range: -2.7565
Max Act: 2.6765. Min Act: -0.1700
Data Index: 4067797 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7565. Min Range: -2.7565
Max Act: 2.6765. Min Act: -0.1700
Data Index: 2586667 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7565. Min Range: -2.7565
Max Act: 2.6765. Min Act: -0.1700
Data Index: 580588 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7565. Min Range: -2.7565
Max Act: 2.6605. Min Act: -0.1700
Data Index: 2781737 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7565. Min Range: -2.7565
Max Act: 2.6445. Min Act: -0.1700
Data Index: 73007 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7565. Min Range: -2.7565
Max Act: 2.6605. Min Act: -0.1700
Data Index: 1094954 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7565. Min Range: -2.7565
Max Act: 2.6605. Min Act: -0.1700
Data Index: 972014 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7565. Min Range: -2.7565
Max Act: 2.6284. Min Act: -0.1700
Data Index: 536384 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7565. Min Range: -2.7565
Max Act: 2.6605. Min Act: -0.1700
Data Index: 5509732 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7565. Min Range: -2.7565
Max Act: 2.6445. Min Act: -0.1700
Data Index: 6693708 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7565. Min Range: -2.7565
Max Act: 2.6445. Min Act: -0.1700
Data Index: 5212375 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #19