Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4642 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1921. Min Range: -5.1921
Max Act: 5.1921. Min Act: -0.1700
Data Index: 5514145 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1921. Min Range: -5.1921
Max Act: 5.0984. Min Act: -0.1700
Data Index: 8678642 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1921. Min Range: -5.1921
Max Act: 5.0984. Min Act: -0.1700
Data Index: 3965698 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1921. Min Range: -5.1921
Max Act: 5.0671. Min Act: -0.1700
Data Index: 8102631 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1921. Min Range: -5.1921
Max Act: 5.0359. Min Act: -0.1700
Data Index: 3585477 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1921. Min Range: -5.1921
Max Act: 4.9734. Min Act: -0.1700
Data Index: 7426183 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1921. Min Range: -5.1921
Max Act: 4.9109. Min Act: -0.1700
Data Index: 8276600 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1921. Min Range: -5.1921
Max Act: 4.9734. Min Act: -0.1700
Data Index: 6009226 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1921. Min Range: -5.1921
Max Act: 4.8796. Min Act: -0.1700
Data Index: 51415 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1921. Min Range: -5.1921
Max Act: 4.8484. Min Act: -0.1700
Data Index: 4444442 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1921. Min Range: -5.1921
Max Act: 4.8484. Min Act: -0.1700
Data Index: 718863 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1921. Min Range: -5.1921
Max Act: 4.7859. Min Act: -0.1700
Data Index: 1963892 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1921. Min Range: -5.1921
Max Act: 4.7859. Min Act: -0.1700
Data Index: 1963885 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1921. Min Range: -5.1921
Max Act: 4.7859. Min Act: -0.1700
Data Index: 621374 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1921. Min Range: -5.1921
Max Act: 4.7546. Min Act: -0.1700
Data Index: 3025513 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1921. Min Range: -5.1921
Max Act: 4.7546. Min Act: -0.1700
Data Index: 7161802 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1921. Min Range: -5.1921
Max Act: 4.7546. Min Act: -0.1700
Data Index: 4673268 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1921. Min Range: -5.1921
Max Act: 4.6921. Min Act: -0.1700
Data Index: 7285498 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1921. Min Range: -5.1921
Max Act: 4.6921. Min Act: -0.1700
Data Index: 4718459 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1921. Min Range: -5.1921
Max Act: 4.6609. Min Act: -0.1700
Data Index: 6146367 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #19