Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4064 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0798. Min Range: -6.0798
Max Act: 6.0798. Min Act: -0.1700
Data Index: 755162 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0798. Min Range: -6.0798
Max Act: 6.0798. Min Act: -0.1700
Data Index: 8243058 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0798. Min Range: -6.0798
Max Act: 6.0485. Min Act: -0.1700
Data Index: 390131 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0798. Min Range: -6.0798
Max Act: 6.0173. Min Act: -0.1700
Data Index: 5951509 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0798. Min Range: -6.0798
Max Act: 5.9860. Min Act: -0.1700
Data Index: 250618 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0798. Min Range: -6.0798
Max Act: 5.9548. Min Act: -0.1700
Data Index: 8580768 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0798. Min Range: -6.0798
Max Act: 5.8923. Min Act: -0.1700
Data Index: 3924294 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0798. Min Range: -6.0798
Max Act: 5.8923. Min Act: -0.1700
Data Index: 2784089 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0798. Min Range: -6.0798
Max Act: 5.8610. Min Act: -0.1700
Data Index: 127354 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0798. Min Range: -6.0798
Max Act: 5.8923. Min Act: -0.1700
Data Index: 4716594 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0798. Min Range: -6.0798
Max Act: 5.7985. Min Act: -0.1700
Data Index: 1639753 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0798. Min Range: -6.0798
Max Act: 5.7048. Min Act: -0.1700
Data Index: 2084322 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0798. Min Range: -6.0798
Max Act: 5.6735. Min Act: -0.1700
Data Index: 3093769 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0798. Min Range: -6.0798
Max Act: 5.6735. Min Act: -0.1700
Data Index: 642710 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0798. Min Range: -6.0798
Max Act: 5.6110. Min Act: -0.1700
Data Index: 589554 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0798. Min Range: -6.0798
Max Act: 5.5798. Min Act: -0.1700
Data Index: 4767126 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0798. Min Range: -6.0798
Max Act: 5.6110. Min Act: -0.1700
Data Index: 674089 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0798. Min Range: -6.0798
Max Act: 5.6110. Min Act: -0.1700
Data Index: 2673003 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0798. Min Range: -6.0798
Max Act: 5.5798. Min Act: -0.1700
Data Index: 2483533 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0798. Min Range: -6.0798
Max Act: 5.5798. Min Act: -0.1700
Data Index: 6289019 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19