Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3127 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0324. Min Range: -7.0324
Max Act: 7.0324. Min Act: -0.1700
Data Index: 150072 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0324. Min Range: -7.0324
Max Act: 7.0011. Min Act: -0.1700
Data Index: 7875239 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0324. Min Range: -7.0324
Max Act: 6.8761. Min Act: -0.1700
Data Index: 3394654 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0324. Min Range: -7.0324
Max Act: 6.8761. Min Act: -0.1700
Data Index: 350062 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0324. Min Range: -7.0324
Max Act: 6.8449. Min Act: -0.1700
Data Index: 2940418 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0324. Min Range: -7.0324
Max Act: 6.8449. Min Act: -0.1700
Data Index: 7209048 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0324. Min Range: -7.0324
Max Act: 6.8136. Min Act: -0.1700
Data Index: 5478019 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0324. Min Range: -7.0324
Max Act: 6.8136. Min Act: -0.1700
Data Index: 6530876 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0324. Min Range: -7.0324
Max Act: 6.7824. Min Act: -0.1700
Data Index: 6797603 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0324. Min Range: -7.0324
Max Act: 6.7511. Min Act: -0.1700
Data Index: 2711247 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0324. Min Range: -7.0324
Max Act: 6.7511. Min Act: -0.1700
Data Index: 5083149 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0324. Min Range: -7.0324
Max Act: 6.7511. Min Act: -0.1700
Data Index: 1217714 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0324. Min Range: -7.0324
Max Act: 6.7199. Min Act: -0.1700
Data Index: 8052647 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0324. Min Range: -7.0324
Max Act: 6.7511. Min Act: -0.1700
Data Index: 4619285 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0324. Min Range: -7.0324
Max Act: 6.6886. Min Act: -0.1700
Data Index: 333361 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0324. Min Range: -7.0324
Max Act: 6.7199. Min Act: -0.1700
Data Index: 2982504 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0324. Min Range: -7.0324
Max Act: 6.6886. Min Act: -0.1700
Data Index: 6101028 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0324. Min Range: -7.0324
Max Act: 6.6574. Min Act: -0.1700
Data Index: 4209908 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0324. Min Range: -7.0324
Max Act: 6.6574. Min Act: -0.1700
Data Index: 7280455 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0324. Min Range: -7.0324
Max Act: 6.6574. Min Act: -0.1700
Data Index: 3879300 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #19