Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4931 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2756. Min Range: -7.2756
Max Act: 7.2756. Min Act: -0.1700
Data Index: 3116067 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2756. Min Range: -7.2756
Max Act: 7.2131. Min Act: -0.1700
Data Index: 3101848 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2756. Min Range: -7.2756
Max Act: 6.9006. Min Act: -0.1700
Data Index: 704183 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2756. Min Range: -7.2756
Max Act: 6.8381. Min Act: -0.1700
Data Index: 3936184 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2756. Min Range: -7.2756
Max Act: 6.8381. Min Act: -0.1700
Data Index: 6276671 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2756. Min Range: -7.2756
Max Act: 6.8069. Min Act: -0.1700
Data Index: 3116072 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2756. Min Range: -7.2756
Max Act: 6.7756. Min Act: -0.1700
Data Index: 7920139 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2756. Min Range: -7.2756
Max Act: 6.7444. Min Act: -0.1700
Data Index: 6939054 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2756. Min Range: -7.2756
Max Act: 6.7444. Min Act: -0.1700
Data Index: 5244428 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2756. Min Range: -7.2756
Max Act: 6.6819. Min Act: -0.1700
Data Index: 8583133 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2756. Min Range: -7.2756
Max Act: 6.6819. Min Act: -0.1700
Data Index: 8065238 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2756. Min Range: -7.2756
Max Act: 6.6194. Min Act: -0.1700
Data Index: 2905520 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2756. Min Range: -7.2756
Max Act: 6.6506. Min Act: -0.1700
Data Index: 7358915 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2756. Min Range: -7.2756
Max Act: 6.6506. Min Act: -0.1700
Data Index: 4198911 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2756. Min Range: -7.2756
Max Act: 6.6819. Min Act: -0.1700
Data Index: 110957 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2756. Min Range: -7.2756
Max Act: 6.6506. Min Act: -0.1700
Data Index: 386480 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2756. Min Range: -7.2756
Max Act: 6.6194. Min Act: -0.1700
Data Index: 4951028 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2756. Min Range: -7.2756
Max Act: 6.6506. Min Act: -0.1700
Data Index: 2388155 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2756. Min Range: -7.2756
Max Act: 6.6194. Min Act: -0.1700
Data Index: 6713563 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2756. Min Range: -7.2756
Max Act: 6.6194. Min Act: -0.1700
Data Index: 3116074 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #19