Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5078 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0500. Min Range: -5.0500
Max Act: 5.0500. Min Act: -0.1700
Data Index: 6813696 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0500. Min Range: -5.0500
Max Act: 4.9563. Min Act: -0.1700
Data Index: 4643829 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0500. Min Range: -5.0500
Max Act: 4.9250. Min Act: -0.1700
Data Index: 6717319 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0500. Min Range: -5.0500
Max Act: 4.8938. Min Act: -0.1700
Data Index: 8353429 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0500. Min Range: -5.0500
Max Act: 4.8625. Min Act: -0.1700
Data Index: 7660870 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0500. Min Range: -5.0500
Max Act: 4.8625. Min Act: -0.1700
Data Index: 7114646 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0500. Min Range: -5.0500
Max Act: 4.8313. Min Act: -0.1700
Data Index: 8131418 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0500. Min Range: -5.0500
Max Act: 4.8000. Min Act: -0.1700
Data Index: 4141410 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0500. Min Range: -5.0500
Max Act: 4.7375. Min Act: -0.1700
Data Index: 2141445 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0500. Min Range: -5.0500
Max Act: 4.7375. Min Act: -0.1700
Data Index: 5612276 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0500. Min Range: -5.0500
Max Act: 4.7063. Min Act: -0.1700
Data Index: 7033779 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0500. Min Range: -5.0500
Max Act: 4.7063. Min Act: -0.1700
Data Index: 3159670 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0500. Min Range: -5.0500
Max Act: 4.6750. Min Act: -0.1700
Data Index: 524709 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0500. Min Range: -5.0500
Max Act: 4.6750. Min Act: -0.1700
Data Index: 7827717 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0500. Min Range: -5.0500
Max Act: 4.6438. Min Act: -0.1700
Data Index: 7613987 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0500. Min Range: -5.0500
Max Act: 4.6438. Min Act: -0.1700
Data Index: 4240475 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0500. Min Range: -5.0500
Max Act: 4.6750. Min Act: -0.1700
Data Index: 524708 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0500. Min Range: -5.0500
Max Act: 4.6125. Min Act: -0.1700
Data Index: 196000 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0500. Min Range: -5.0500
Max Act: 4.6125. Min Act: -0.1700
Data Index: 2034212 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0500. Min Range: -5.0500
Max Act: 4.5813. Min Act: -0.1700
Data Index: 48653 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #19