Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3637 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5476. Min Range: -4.5476
Max Act: 4.5476. Min Act: -0.1700
Data Index: 860114 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5476. Min Range: -4.5476
Max Act: 4.5476. Min Act: -0.1700
Data Index: 6042503 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5476. Min Range: -4.5476
Max Act: 4.5164. Min Act: -0.1700
Data Index: 6881722 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5476. Min Range: -4.5476
Max Act: 4.4851. Min Act: -0.1700
Data Index: 3678446 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5476. Min Range: -4.5476
Max Act: 4.4539. Min Act: -0.1700
Data Index: 6520875 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5476. Min Range: -4.5476
Max Act: 4.4539. Min Act: -0.1700
Data Index: 3381196 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5476. Min Range: -4.5476
Max Act: 4.4226. Min Act: -0.1700
Data Index: 1019887 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5476. Min Range: -4.5476
Max Act: 4.4226. Min Act: -0.1700
Data Index: 6739695 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5476. Min Range: -4.5476
Max Act: 4.4226. Min Act: -0.1700
Data Index: 5364557 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5476. Min Range: -4.5476
Max Act: 4.3914. Min Act: -0.1700
Data Index: 3257632 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5476. Min Range: -4.5476
Max Act: 4.3914. Min Act: -0.1700
Data Index: 6771892 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5476. Min Range: -4.5476
Max Act: 4.3914. Min Act: -0.1700
Data Index: 5201381 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5476. Min Range: -4.5476
Max Act: 4.4226. Min Act: -0.1686
Data Index: 3131362 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5476. Min Range: -4.5476
Max Act: 4.3914. Min Act: -0.1700
Data Index: 6947697 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5476. Min Range: -4.5476
Max Act: 4.3601. Min Act: -0.1700
Data Index: 4456621 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5476. Min Range: -4.5476
Max Act: 4.3601. Min Act: -0.1700
Data Index: 622698 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5476. Min Range: -4.5476
Max Act: 4.3601. Min Act: -0.1700
Data Index: 2250551 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5476. Min Range: -4.5476
Max Act: 4.3289. Min Act: -0.1700
Data Index: 5510936 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5476. Min Range: -4.5476
Max Act: 4.3289. Min Act: -0.1700
Data Index: 4291523 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5476. Min Range: -4.5476
Max Act: 4.3289. Min Act: -0.1700
Data Index: 4160625 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #19