Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2952 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3877. Min Range: -9.3877
Max Act: 9.3877. Min Act: -0.1700
Data Index: 4017808 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3877. Min Range: -9.3877
Max Act: 9.2627. Min Act: -0.1700
Data Index: 6638004 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3877. Min Range: -9.3877
Max Act: 9.2002. Min Act: -0.1700
Data Index: 4062370 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3877. Min Range: -9.3877
Max Act: 9.1377. Min Act: -0.1700
Data Index: 6614817 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3877. Min Range: -9.3877
Max Act: 9.0752. Min Act: -0.1700
Data Index: 3786976 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3877. Min Range: -9.3877
Max Act: 9.0127. Min Act: -0.1700
Data Index: 6702080 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3877. Min Range: -9.3877
Max Act: 9.0127. Min Act: -0.1700
Data Index: 6225295 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3877. Min Range: -9.3877
Max Act: 9.0127. Min Act: -0.1700
Data Index: 362529 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3877. Min Range: -9.3877
Max Act: 8.9502. Min Act: -0.1700
Data Index: 8828411 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3877. Min Range: -9.3877
Max Act: 8.9502. Min Act: -0.1700
Data Index: 6224395 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3877. Min Range: -9.3877
Max Act: 8.8877. Min Act: -0.1700
Data Index: 2126598 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3877. Min Range: -9.3877
Max Act: 8.8877. Min Act: -0.1700
Data Index: 5298208 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3877. Min Range: -9.3877
Max Act: 8.8877. Min Act: -0.1700
Data Index: 8108110 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3877. Min Range: -9.3877
Max Act: 8.8252. Min Act: -0.1700
Data Index: 7471593 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3877. Min Range: -9.3877
Max Act: 8.8252. Min Act: -0.1700
Data Index: 422939 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3877. Min Range: -9.3877
Max Act: 8.8252. Min Act: -0.1700
Data Index: 3537680 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3877. Min Range: -9.3877
Max Act: 8.8252. Min Act: -0.1700
Data Index: 6393952 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3877. Min Range: -9.3877
Max Act: 8.8252. Min Act: -0.1700
Data Index: 7251323 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3877. Min Range: -9.3877
Max Act: 8.8252. Min Act: -0.1700
Data Index: 4122158 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3877. Min Range: -9.3877
Max Act: 8.8252. Min Act: -0.1700
Data Index: 3082018 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19