Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3100 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5520. Min Range: -3.5520
Max Act: 3.5520. Min Act: -0.1700
Data Index: 2990699 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5520. Min Range: -3.5520
Max Act: 3.5520. Min Act: -0.1700
Data Index: 2291426 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5520. Min Range: -3.5520
Max Act: 3.4894. Min Act: -0.1700
Data Index: 2356810 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5520. Min Range: -3.5520
Max Act: 3.4894. Min Act: -0.1700
Data Index: 3797354 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5520. Min Range: -3.5520
Max Act: 3.4894. Min Act: -0.1700
Data Index: 6811182 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5520. Min Range: -3.5520
Max Act: 3.4894. Min Act: -0.1700
Data Index: 1290616 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5520. Min Range: -3.5520
Max Act: 3.5207. Min Act: -0.1700
Data Index: 5484640 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5520. Min Range: -3.5520
Max Act: 3.4581. Min Act: -0.1700
Data Index: 999962 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5520. Min Range: -3.5520
Max Act: 3.4267. Min Act: -0.1700
Data Index: 785575 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5520. Min Range: -3.5520
Max Act: 3.4267. Min Act: -0.1700
Data Index: 3683890 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5520. Min Range: -3.5520
Max Act: 3.4267. Min Act: -0.1700
Data Index: 522086 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5520. Min Range: -3.5520
Max Act: 3.4267. Min Act: -0.1700
Data Index: 8001784 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5520. Min Range: -3.5520
Max Act: 3.4267. Min Act: -0.1700
Data Index: 6473889 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5520. Min Range: -3.5520
Max Act: 3.4267. Min Act: -0.1700
Data Index: 4448910 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5520. Min Range: -3.5520
Max Act: 3.4267. Min Act: -0.1700
Data Index: 3686122 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5520. Min Range: -3.5520
Max Act: 3.4267. Min Act: -0.1700
Data Index: 1951498 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5520. Min Range: -3.5520
Max Act: 3.4267. Min Act: -0.1700
Data Index: 1686982 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5520. Min Range: -3.5520
Max Act: 3.4267. Min Act: -0.1700
Data Index: 1584460 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5520. Min Range: -3.5520
Max Act: 3.3954. Min Act: -0.1700
Data Index: 3179757 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5520. Min Range: -3.5520
Max Act: 3.3954. Min Act: -0.1700
Data Index: 938887 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19