Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2772 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9534. Min Range: -4.9534
Max Act: 4.9534. Min Act: -0.1700
Data Index: 3683128 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9534. Min Range: -4.9534
Max Act: 4.9221. Min Act: -0.1700
Data Index: 6049594 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9534. Min Range: -4.9534
Max Act: 4.8909. Min Act: -0.1700
Data Index: 743688 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9534. Min Range: -4.9534
Max Act: 4.8909. Min Act: -0.1700
Data Index: 4837500 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9534. Min Range: -4.9534
Max Act: 4.8596. Min Act: -0.1700
Data Index: 8484361 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9534. Min Range: -4.9534
Max Act: 4.8596. Min Act: -0.1700
Data Index: 7920634 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9534. Min Range: -4.9534
Max Act: 4.7971. Min Act: -0.1700
Data Index: 848523 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9534. Min Range: -4.9534
Max Act: 4.8284. Min Act: -0.1700
Data Index: 1751405 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9534. Min Range: -4.9534
Max Act: 4.8284. Min Act: -0.1700
Data Index: 424635 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9534. Min Range: -4.9534
Max Act: 4.7971. Min Act: -0.1700
Data Index: 807426 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9534. Min Range: -4.9534
Max Act: 4.8284. Min Act: -0.1700
Data Index: 7566232 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9534. Min Range: -4.9534
Max Act: 4.7971. Min Act: -0.1700
Data Index: 3587158 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9534. Min Range: -4.9534
Max Act: 4.7971. Min Act: -0.1700
Data Index: 6306278 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9534. Min Range: -4.9534
Max Act: 4.7971. Min Act: -0.1700
Data Index: 1343561 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9534. Min Range: -4.9534
Max Act: 4.7971. Min Act: -0.1700
Data Index: 4850616 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9534. Min Range: -4.9534
Max Act: 4.7971. Min Act: -0.1700
Data Index: 5868708 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9534. Min Range: -4.9534
Max Act: 4.7659. Min Act: -0.1700
Data Index: 6293985 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9534. Min Range: -4.9534
Max Act: 4.7659. Min Act: -0.1700
Data Index: 6493433 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9534. Min Range: -4.9534
Max Act: 4.7659. Min Act: -0.1700
Data Index: 17213 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9534. Min Range: -4.9534
Max Act: 4.7659. Min Act: -0.1700
Data Index: 8244920 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #19