Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4419 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9734. Min Range: -5.9734
Max Act: 5.9734. Min Act: -0.1700
Data Index: 8219063 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9734. Min Range: -5.9734
Max Act: 5.9109. Min Act: -0.1700
Data Index: 3122865 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9734. Min Range: -5.9734
Max Act: 5.9421. Min Act: -0.1700
Data Index: 3133580 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9734. Min Range: -5.9734
Max Act: 5.9109. Min Act: -0.1700
Data Index: 1815520 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9734. Min Range: -5.9734
Max Act: 5.8484. Min Act: -0.1700
Data Index: 5452412 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9734. Min Range: -5.9734
Max Act: 5.7859. Min Act: -0.1700
Data Index: 5523737 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9734. Min Range: -5.9734
Max Act: 5.7859. Min Act: -0.1700
Data Index: 815386 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9734. Min Range: -5.9734
Max Act: 5.7546. Min Act: -0.1700
Data Index: 931416 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9734. Min Range: -5.9734
Max Act: 5.7546. Min Act: -0.1700
Data Index: 6114691 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9734. Min Range: -5.9734
Max Act: 5.6921. Min Act: -0.1700
Data Index: 2586530 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9734. Min Range: -5.9734
Max Act: 5.7234. Min Act: -0.1700
Data Index: 720875 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9734. Min Range: -5.9734
Max Act: 5.6921. Min Act: -0.1700
Data Index: 7186168 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9734. Min Range: -5.9734
Max Act: 5.7234. Min Act: -0.1700
Data Index: 2727874 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9734. Min Range: -5.9734
Max Act: 5.6609. Min Act: -0.1700
Data Index: 5904382 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9734. Min Range: -5.9734
Max Act: 5.6921. Min Act: -0.1700
Data Index: 5193971 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9734. Min Range: -5.9734
Max Act: 5.6296. Min Act: -0.1700
Data Index: 738771 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9734. Min Range: -5.9734
Max Act: 5.6921. Min Act: -0.1700
Data Index: 534319 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9734. Min Range: -5.9734
Max Act: 5.6609. Min Act: -0.1700
Data Index: 5617461 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9734. Min Range: -5.9734
Max Act: 5.6609. Min Act: -0.1700
Data Index: 5029084 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9734. Min Range: -5.9734
Max Act: 5.6296. Min Act: -0.1700
Data Index: 6529209 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #19