Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3549 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9233. Min Range: -3.9233
Max Act: 3.8921. Min Act: -0.1700
Data Index: 3407294 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9233. Min Range: -3.9233
Max Act: 3.9233. Min Act: -0.1700
Data Index: 6956631 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9233. Min Range: -3.9233
Max Act: 3.8764. Min Act: -0.1700
Data Index: 5153530 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9233. Min Range: -3.9233
Max Act: 3.8295. Min Act: -0.1700
Data Index: 1902251 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9233. Min Range: -3.9233
Max Act: 3.7670. Min Act: -0.1700
Data Index: 2621362 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9233. Min Range: -3.9233
Max Act: 3.7670. Min Act: -0.1700
Data Index: 3395410 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9233. Min Range: -3.9233
Max Act: 3.7514. Min Act: -0.1700
Data Index: 1647126 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9233. Min Range: -3.9233
Max Act: 3.7357. Min Act: -0.1700
Data Index: 5717898 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9233. Min Range: -3.9233
Max Act: 3.7044. Min Act: -0.1700
Data Index: 5488240 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9233. Min Range: -3.9233
Max Act: 3.6888. Min Act: -0.1700
Data Index: 8433779 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9233. Min Range: -3.9233
Max Act: 3.6888. Min Act: -0.1700
Data Index: 3891996 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9233. Min Range: -3.9233
Max Act: 3.6575. Min Act: -0.1700
Data Index: 6276091 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9233. Min Range: -3.9233
Max Act: 3.6731. Min Act: -0.1700
Data Index: 5020987 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9233. Min Range: -3.9233
Max Act: 3.6731. Min Act: -0.1700
Data Index: 8362922 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9233. Min Range: -3.9233
Max Act: 3.6575. Min Act: -0.1700
Data Index: 5770773 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9233. Min Range: -3.9233
Max Act: 3.6731. Min Act: -0.1700
Data Index: 1048209 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9233. Min Range: -3.9233
Max Act: 3.6731. Min Act: -0.1700
Data Index: 3729933 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9233. Min Range: -3.9233
Max Act: 3.6419. Min Act: -0.1700
Data Index: 4185343 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9233. Min Range: -3.9233
Max Act: 3.6575. Min Act: -0.1700
Data Index: 8708682 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9233. Min Range: -3.9233
Max Act: 3.6731. Min Act: -0.1700
Data Index: 777532 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #19