Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3792 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5595. Min Range: -6.5595
Max Act: 6.5595. Min Act: -0.1700
Data Index: 711172 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5595. Min Range: -6.5595
Max Act: 6.5282. Min Act: -0.1700
Data Index: 6444612 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5595. Min Range: -6.5595
Max Act: 6.4970. Min Act: -0.1700
Data Index: 4200612 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5595. Min Range: -6.5595
Max Act: 6.4657. Min Act: -0.1700
Data Index: 1304714 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5595. Min Range: -6.5595
Max Act: 6.4657. Min Act: -0.1700
Data Index: 5756967 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5595. Min Range: -6.5595
Max Act: 6.4657. Min Act: -0.1700
Data Index: 2770804 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5595. Min Range: -6.5595
Max Act: 6.4345. Min Act: -0.1700
Data Index: 6816746 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5595. Min Range: -6.5595
Max Act: 6.4345. Min Act: -0.1700
Data Index: 570644 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5595. Min Range: -6.5595
Max Act: 6.4032. Min Act: -0.1700
Data Index: 6033203 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5595. Min Range: -6.5595
Max Act: 6.3720. Min Act: -0.1700
Data Index: 7123632 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5595. Min Range: -6.5595
Max Act: 6.3720. Min Act: -0.1700
Data Index: 5756975 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5595. Min Range: -6.5595
Max Act: 6.3720. Min Act: -0.1700
Data Index: 7565090 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5595. Min Range: -6.5595
Max Act: 6.3407. Min Act: -0.1700
Data Index: 4366824 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5595. Min Range: -6.5595
Max Act: 6.3407. Min Act: -0.1700
Data Index: 3357189 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5595. Min Range: -6.5595
Max Act: 6.3407. Min Act: -0.1700
Data Index: 746557 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5595. Min Range: -6.5595
Max Act: 6.2782. Min Act: -0.1700
Data Index: 1854560 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5595. Min Range: -6.5595
Max Act: 6.3095. Min Act: -0.1700
Data Index: 7626192 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5595. Min Range: -6.5595
Max Act: 6.3095. Min Act: -0.1700
Data Index: 903756 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5595. Min Range: -6.5595
Max Act: 6.3095. Min Act: -0.1700
Data Index: 4087554 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5595. Min Range: -6.5595
Max Act: 6.2782. Min Act: -0.1700
Data Index: 3812207 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #19