Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6390 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0892. Min Range: -8.0892
Max Act: 8.0892. Min Act: -0.1700
Data Index: 8818907 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0892. Min Range: -8.0892
Max Act: 8.0892. Min Act: -0.1700
Data Index: 8571773 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0892. Min Range: -8.0892
Max Act: 8.0579. Min Act: -0.1700
Data Index: 1020928 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0892. Min Range: -8.0892
Max Act: 7.9954. Min Act: -0.1700
Data Index: 8818927 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0892. Min Range: -8.0892
Max Act: 7.9017. Min Act: -0.1700
Data Index: 1020929 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0892. Min Range: -8.0892
Max Act: 7.8079. Min Act: -0.1700
Data Index: 2608421 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0892. Min Range: -8.0892
Max Act: 7.8079. Min Act: -0.1700
Data Index: 890948 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0892. Min Range: -8.0892
Max Act: 7.7142. Min Act: -0.1700
Data Index: 1020930 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0892. Min Range: -8.0892
Max Act: 7.6829. Min Act: -0.1700
Data Index: 4368653 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0892. Min Range: -8.0892
Max Act: 7.6829. Min Act: -0.1700
Data Index: 3497744 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0892. Min Range: -8.0892
Max Act: 7.6517. Min Act: -0.1700
Data Index: 4696198 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0892. Min Range: -8.0892
Max Act: 7.6517. Min Act: -0.1700
Data Index: 6159640 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0892. Min Range: -8.0892
Max Act: 7.6517. Min Act: -0.1700
Data Index: 6296713 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0892. Min Range: -8.0892
Max Act: 7.6204. Min Act: -0.1700
Data Index: 2428985 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0892. Min Range: -8.0892
Max Act: 7.5579. Min Act: -0.1700
Data Index: 8307166 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0892. Min Range: -8.0892
Max Act: 7.5892. Min Act: -0.1700
Data Index: 8642070 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0892. Min Range: -8.0892
Max Act: 7.5579. Min Act: -0.1700
Data Index: 8201179 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0892. Min Range: -8.0892
Max Act: 7.5267. Min Act: -0.1700
Data Index: 7818237 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0892. Min Range: -8.0892
Max Act: 7.5267. Min Act: -0.1700
Data Index: 1654264 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0892. Min Range: -8.0892
Max Act: 7.5579. Min Act: -0.1700
Data Index: 2589982 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19