Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2552 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.7753. Min Range: -8.7753
Max Act: 8.7753. Min Act: -0.1700
Data Index: 5720907 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7753. Min Range: -8.7753
Max Act: 8.3378. Min Act: -0.1700
Data Index: 5109748 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7753. Min Range: -8.7753
Max Act: 8.1503. Min Act: -0.1700
Data Index: 8125874 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7753. Min Range: -8.7753
Max Act: 8.2128. Min Act: -0.1700
Data Index: 5333111 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7753. Min Range: -8.7753
Max Act: 8.1503. Min Act: -0.1700
Data Index: 5559530 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7753. Min Range: -8.7753
Max Act: 8.1503. Min Act: -0.1700
Data Index: 3795487 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7753. Min Range: -8.7753
Max Act: 8.1503. Min Act: -0.1700
Data Index: 4081526 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7753. Min Range: -8.7753
Max Act: 8.1503. Min Act: -0.1700
Data Index: 18571 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7753. Min Range: -8.7753
Max Act: 8.1503. Min Act: -0.1700
Data Index: 8200705 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7753. Min Range: -8.7753
Max Act: 8.0878. Min Act: -0.1700
Data Index: 1223711 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7753. Min Range: -8.7753
Max Act: 8.0878. Min Act: -0.1700
Data Index: 1038507 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7753. Min Range: -8.7753
Max Act: 8.0878. Min Act: -0.1700
Data Index: 5342859 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7753. Min Range: -8.7753
Max Act: 8.0253. Min Act: -0.1700
Data Index: 5938865 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7753. Min Range: -8.7753
Max Act: 7.9628. Min Act: -0.1700
Data Index: 1682351 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7753. Min Range: -8.7753
Max Act: 8.0253. Min Act: -0.1700
Data Index: 2350072 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7753. Min Range: -8.7753
Max Act: 8.0253. Min Act: -0.1700
Data Index: 1337741 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7753. Min Range: -8.7753
Max Act: 8.0253. Min Act: -0.1700
Data Index: 7708837 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7753. Min Range: -8.7753
Max Act: 7.9003. Min Act: -0.1700
Data Index: 1982655 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7753. Min Range: -8.7753
Max Act: 7.9003. Min Act: -0.1700
Data Index: 5333114 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7753. Min Range: -8.7753
Max Act: 7.8378. Min Act: -0.1700
Data Index: 3070432 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #19