Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3803 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5035. Min Range: -8.5035
Max Act: 8.5035. Min Act: -0.1700
Data Index: 1659387 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5035. Min Range: -8.5035
Max Act: 8.3785. Min Act: -0.1700
Data Index: 479920 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5035. Min Range: -8.5035
Max Act: 8.2535. Min Act: -0.1700
Data Index: 201011 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5035. Min Range: -8.5035
Max Act: 8.1285. Min Act: -0.1700
Data Index: 4112232 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5035. Min Range: -8.5035
Max Act: 8.0660. Min Act: -0.1700
Data Index: 5389844 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5035. Min Range: -8.5035
Max Act: 8.0660. Min Act: -0.1700
Data Index: 2490170 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5035. Min Range: -8.5035
Max Act: 8.0035. Min Act: -0.1700
Data Index: 5567067 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5035. Min Range: -8.5035
Max Act: 8.0035. Min Act: -0.1700
Data Index: 8115367 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5035. Min Range: -8.5035
Max Act: 8.0035. Min Act: -0.1700
Data Index: 7274095 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5035. Min Range: -8.5035
Max Act: 7.8160. Min Act: -0.1700
Data Index: 6649621 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5035. Min Range: -8.5035
Max Act: 7.8785. Min Act: -0.1700
Data Index: 4085868 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5035. Min Range: -8.5035
Max Act: 7.8160. Min Act: -0.1700
Data Index: 3225789 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5035. Min Range: -8.5035
Max Act: 7.8160. Min Act: -0.1700
Data Index: 1218696 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5035. Min Range: -8.5035
Max Act: 7.7535. Min Act: -0.1700
Data Index: 7476376 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5035. Min Range: -8.5035
Max Act: 7.7223. Min Act: -0.1700
Data Index: 7590273 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5035. Min Range: -8.5035
Max Act: 7.7223. Min Act: -0.1700
Data Index: 932634 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5035. Min Range: -8.5035
Max Act: 7.7535. Min Act: -0.1700
Data Index: 3546667 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5035. Min Range: -8.5035
Max Act: 7.6910. Min Act: -0.1700
Data Index: 3089637 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5035. Min Range: -8.5035
Max Act: 7.6598. Min Act: -0.1700
Data Index: 3587814 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5035. Min Range: -8.5035
Max Act: 7.6598. Min Act: -0.1700
Data Index: 6769254 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19