Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3712 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4381. Min Range: -3.4381
Max Act: 3.4381. Min Act: -0.1700
Data Index: 959362 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4381. Min Range: -3.4381
Max Act: 3.3440. Min Act: -0.1700
Data Index: 4478157 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4381. Min Range: -3.4381
Max Act: 3.3126. Min Act: -0.1700
Data Index: 5665675 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4381. Min Range: -3.4381
Max Act: 3.3126. Min Act: -0.1700
Data Index: 8290763 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4381. Min Range: -3.4381
Max Act: 3.3126. Min Act: -0.1700
Data Index: 8172719 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4381. Min Range: -3.4381
Max Act: 3.3126. Min Act: -0.1700
Data Index: 7770992 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4381. Min Range: -3.4381
Max Act: 3.3126. Min Act: -0.1700
Data Index: 3955787 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4381. Min Range: -3.4381
Max Act: 3.3126. Min Act: -0.1700
Data Index: 3678078 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4381. Min Range: -3.4381
Max Act: 3.3126. Min Act: -0.1700
Data Index: 3407564 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4381. Min Range: -3.4381
Max Act: 3.3126. Min Act: -0.1700
Data Index: 6531834 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4381. Min Range: -3.4381
Max Act: 3.3126. Min Act: -0.1700
Data Index: 5710098 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4381. Min Range: -3.4381
Max Act: 3.2812. Min Act: -0.1700
Data Index: 372747 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4381. Min Range: -3.4381
Max Act: 3.2812. Min Act: -0.1700
Data Index: 7731725 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4381. Min Range: -3.4381
Max Act: 3.2812. Min Act: -0.1700
Data Index: 249891 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4381. Min Range: -3.4381
Max Act: 3.2812. Min Act: -0.1700
Data Index: 3357297 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4381. Min Range: -3.4381
Max Act: 3.2812. Min Act: -0.1700
Data Index: 6181368 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4381. Min Range: -3.4381
Max Act: 3.2812. Min Act: -0.1700
Data Index: 1951810 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4381. Min Range: -3.4381
Max Act: 3.2812. Min Act: -0.1700
Data Index: 8280072 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4381. Min Range: -3.4381
Max Act: 3.2812. Min Act: -0.1700
Data Index: 5370989 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4381. Min Range: -3.4381
Max Act: 3.2498. Min Act: -0.1700
Data Index: 2185643 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19