Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2433 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0525. Min Range: -4.0525
Max Act: 4.0525. Min Act: -0.1700
Data Index: 7872294 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.9900. Min Act: -0.1700
Data Index: 446616 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.9275. Min Act: -0.1700
Data Index: 5998091 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.8649. Min Act: -0.1700
Data Index: 7437021 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.8649. Min Act: -0.1700
Data Index: 5332275 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.8337. Min Act: -0.1700
Data Index: 3296390 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.8337. Min Act: -0.1700
Data Index: 7414693 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.8024. Min Act: -0.1700
Data Index: 5120408 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.8024. Min Act: -0.1700
Data Index: 2481500 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.8337. Min Act: -0.1700
Data Index: 5332705 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.8337. Min Act: -0.1700
Data Index: 5556084 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.8024. Min Act: -0.1700
Data Index: 2593625 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.8024. Min Act: -0.1700
Data Index: 1077070 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.8024. Min Act: -0.1700
Data Index: 968588 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.8337. Min Act: -0.1700
Data Index: 1723467 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.7711. Min Act: -0.1700
Data Index: 4599070 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.7398. Min Act: -0.1700
Data Index: 722566 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.7398. Min Act: -0.1700
Data Index: 5379950 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.7711. Min Act: -0.1700
Data Index: 486506 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.7086. Min Act: -0.1700
Data Index: 1274695 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #19