Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3591 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9736. Min Range: -4.9736
Max Act: 4.9736. Min Act: -0.1700
Data Index: 5057215 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9736. Min Range: -4.9736
Max Act: 4.9111. Min Act: -0.1700
Data Index: 2299300 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9736. Min Range: -4.9736
Max Act: 4.8798. Min Act: -0.1700
Data Index: 3106925 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9736. Min Range: -4.9736
Max Act: 4.8486. Min Act: -0.1700
Data Index: 254442 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9736. Min Range: -4.9736
Max Act: 4.8486. Min Act: -0.1700
Data Index: 1679608 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9736. Min Range: -4.9736
Max Act: 4.7861. Min Act: -0.1700
Data Index: 92126 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9736. Min Range: -4.9736
Max Act: 4.7861. Min Act: -0.1700
Data Index: 1578579 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9736. Min Range: -4.9736
Max Act: 4.7861. Min Act: -0.1700
Data Index: 2142799 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9736. Min Range: -4.9736
Max Act: 4.7548. Min Act: -0.1700
Data Index: 5174636 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9736. Min Range: -4.9736
Max Act: 4.7548. Min Act: -0.1700
Data Index: 6776911 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9736. Min Range: -4.9736
Max Act: 4.7548. Min Act: -0.1700
Data Index: 7796892 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9736. Min Range: -4.9736
Max Act: 4.7548. Min Act: -0.1700
Data Index: 2527312 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9736. Min Range: -4.9736
Max Act: 4.7548. Min Act: -0.1700
Data Index: 8312787 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9736. Min Range: -4.9736
Max Act: 4.7236. Min Act: -0.1700
Data Index: 8310814 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9736. Min Range: -4.9736
Max Act: 4.7236. Min Act: -0.1700
Data Index: 332310 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9736. Min Range: -4.9736
Max Act: 4.7236. Min Act: -0.1700
Data Index: 53174 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9736. Min Range: -4.9736
Max Act: 4.6923. Min Act: -0.1700
Data Index: 789691 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9736. Min Range: -4.9736
Max Act: 4.6923. Min Act: -0.1700
Data Index: 2471238 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9736. Min Range: -4.9736
Max Act: 4.6611. Min Act: -0.1700
Data Index: 5332409 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9736. Min Range: -4.9736
Max Act: 4.6611. Min Act: -0.1700
Data Index: 1595321 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19