Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1037 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2577. Min Range: -4.2577
Max Act: 4.2577. Min Act: -0.1700
Data Index: 5747417 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2577. Min Range: -4.2577
Max Act: 4.0702. Min Act: -0.1700
Data Index: 3207662 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2577. Min Range: -4.2577
Max Act: 4.0077. Min Act: -0.1700
Data Index: 1639451 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2577. Min Range: -4.2577
Max Act: 3.9139. Min Act: -0.1700
Data Index: 6413241 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2577. Min Range: -4.2577
Max Act: 3.9139. Min Act: -0.1700
Data Index: 7214956 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2577. Min Range: -4.2577
Max Act: 3.8826. Min Act: -0.1700
Data Index: 8617949 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2577. Min Range: -4.2577
Max Act: 3.8201. Min Act: -0.1700
Data Index: 8088910 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2577. Min Range: -4.2577
Max Act: 3.8513. Min Act: -0.1700
Data Index: 7162516 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2577. Min Range: -4.2577
Max Act: 3.8201. Min Act: -0.1700
Data Index: 3370326 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2577. Min Range: -4.2577
Max Act: 3.8513. Min Act: -0.1700
Data Index: 3554952 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2577. Min Range: -4.2577
Max Act: 3.8513. Min Act: -0.1700
Data Index: 2687396 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2577. Min Range: -4.2577
Max Act: 3.7888. Min Act: -0.1700
Data Index: 4596420 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2577. Min Range: -4.2577
Max Act: 3.7888. Min Act: -0.1700
Data Index: 2456325 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2577. Min Range: -4.2577
Max Act: 3.7575. Min Act: -0.1700
Data Index: 4788838 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2577. Min Range: -4.2577
Max Act: 3.7575. Min Act: -0.1700
Data Index: 6210959 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2577. Min Range: -4.2577
Max Act: 3.7575. Min Act: -0.1700
Data Index: 4810714 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2577. Min Range: -4.2577
Max Act: 3.7575. Min Act: -0.1700
Data Index: 570529 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2577. Min Range: -4.2577
Max Act: 3.7575. Min Act: -0.1700
Data Index: 4692144 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2577. Min Range: -4.2577
Max Act: 3.7575. Min Act: -0.1700
Data Index: 2793131 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2577. Min Range: -4.2577
Max Act: 3.7262. Min Act: -0.1700
Data Index: 4612893 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19