Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5681 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1617. Min Range: -5.1617
Max Act: 5.1617. Min Act: -0.1700
Data Index: 6916436 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1617. Min Range: -5.1617
Max Act: 5.0680. Min Act: -0.1700
Data Index: 1961282 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1617. Min Range: -5.1617
Max Act: 5.0680. Min Act: -0.1700
Data Index: 6680353 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1617. Min Range: -5.1617
Max Act: 4.9742. Min Act: -0.1700
Data Index: 5774192 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1617. Min Range: -5.1617
Max Act: 5.0055. Min Act: -0.1700
Data Index: 4510016 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1617. Min Range: -5.1617
Max Act: 4.9117. Min Act: -0.1700
Data Index: 212733 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1617. Min Range: -5.1617
Max Act: 4.9117. Min Act: -0.1700
Data Index: 8617494 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1617. Min Range: -5.1617
Max Act: 4.9117. Min Act: -0.1700
Data Index: 783673 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1617. Min Range: -5.1617
Max Act: 4.9117. Min Act: -0.1700
Data Index: 8599561 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1617. Min Range: -5.1617
Max Act: 4.8805. Min Act: -0.1700
Data Index: 2463753 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1617. Min Range: -5.1617
Max Act: 4.8805. Min Act: -0.1700
Data Index: 6968890 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1617. Min Range: -5.1617
Max Act: 4.8492. Min Act: -0.1700
Data Index: 3700071 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1617. Min Range: -5.1617
Max Act: 4.8492. Min Act: -0.1700
Data Index: 5877791 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1617. Min Range: -5.1617
Max Act: 4.8492. Min Act: -0.1700
Data Index: 4001237 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1617. Min Range: -5.1617
Max Act: 4.8180. Min Act: -0.1700
Data Index: 2345804 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1617. Min Range: -5.1617
Max Act: 4.8180. Min Act: -0.1700
Data Index: 3132248 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1617. Min Range: -5.1617
Max Act: 4.8180. Min Act: -0.1700
Data Index: 5531411 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1617. Min Range: -5.1617
Max Act: 4.8180. Min Act: -0.1700
Data Index: 7932349 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1617. Min Range: -5.1617
Max Act: 4.8180. Min Act: -0.1700
Data Index: 8257956 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1617. Min Range: -5.1617
Max Act: 4.7867. Min Act: -0.1700
Data Index: 8449414 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #19