Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6381 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8754. Min Range: -3.8754
Max Act: 3.8754. Min Act: -0.1700
Data Index: 2427411 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8754. Min Range: -3.8754
Max Act: 3.8754. Min Act: -0.1700
Data Index: 3807119 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8754. Min Range: -3.8754
Max Act: 3.8441. Min Act: -0.1700
Data Index: 5042887 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8754. Min Range: -3.8754
Max Act: 3.8441. Min Act: -0.1700
Data Index: 8203333 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8754. Min Range: -3.8754
Max Act: 3.8441. Min Act: -0.1700
Data Index: 772466 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8754. Min Range: -3.8754
Max Act: 3.8441. Min Act: -0.1700
Data Index: 2761246 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8754. Min Range: -3.8754
Max Act: 3.8441. Min Act: -0.1700
Data Index: 7947752 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8754. Min Range: -3.8754
Max Act: 3.8128. Min Act: -0.1700
Data Index: 7513460 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8754. Min Range: -3.8754
Max Act: 3.8128. Min Act: -0.1700
Data Index: 4842736 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8754. Min Range: -3.8754
Max Act: 3.8128. Min Act: -0.1700
Data Index: 4281490 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8754. Min Range: -3.8754
Max Act: 3.8128. Min Act: -0.1700
Data Index: 4084349 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8754. Min Range: -3.8754
Max Act: 3.8128. Min Act: -0.1700
Data Index: 3443166 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8754. Min Range: -3.8754
Max Act: 3.8128. Min Act: -0.1700
Data Index: 75912 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8754. Min Range: -3.8754
Max Act: 3.8128. Min Act: -0.1700
Data Index: 7066713 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8754. Min Range: -3.8754
Max Act: 3.8128. Min Act: -0.1700
Data Index: 6673780 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8754. Min Range: -3.8754
Max Act: 3.8128. Min Act: -0.1700
Data Index: 6492077 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8754. Min Range: -3.8754
Max Act: 3.8128. Min Act: -0.1700
Data Index: 2611743 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8754. Min Range: -3.8754
Max Act: 3.8128. Min Act: -0.1700
Data Index: 5495484 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8754. Min Range: -3.8754
Max Act: 3.7503. Min Act: -0.1700
Data Index: 1681157 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8754. Min Range: -3.8754
Max Act: 3.7816. Min Act: -0.1700
Data Index: 4886744 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19