Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2152 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1699. Min Range: -10.1699
Max Act: 10.1699. Min Act: -0.1700
Data Index: 2654959 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1699. Min Range: -10.1699
Max Act: 10.0449. Min Act: -0.1700
Data Index: 6164562 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1699. Min Range: -10.1699
Max Act: 9.9824. Min Act: -0.1700
Data Index: 7125865 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1699. Min Range: -10.1699
Max Act: 9.9824. Min Act: -0.1700
Data Index: 7874952 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1699. Min Range: -10.1699
Max Act: 9.9824. Min Act: -0.1700
Data Index: 8619904 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1699. Min Range: -10.1699
Max Act: 9.9199. Min Act: -0.1700
Data Index: 2654962 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1699. Min Range: -10.1699
Max Act: 9.8574. Min Act: -0.1700
Data Index: 8532507 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1699. Min Range: -10.1699
Max Act: 9.7324. Min Act: -0.1700
Data Index: 5853121 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1699. Min Range: -10.1699
Max Act: 9.7949. Min Act: -0.1700
Data Index: 6356751 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1699. Min Range: -10.1699
Max Act: 9.7949. Min Act: -0.1700
Data Index: 734869 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1699. Min Range: -10.1699
Max Act: 9.7324. Min Act: -0.1700
Data Index: 4708001 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1699. Min Range: -10.1699
Max Act: 9.7324. Min Act: -0.1700
Data Index: 3453038 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1699. Min Range: -10.1699
Max Act: 9.6699. Min Act: -0.1700
Data Index: 605551 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1699. Min Range: -10.1699
Max Act: 9.6699. Min Act: -0.1700
Data Index: 5167194 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1699. Min Range: -10.1699
Max Act: 9.6699. Min Act: -0.1700
Data Index: 734862 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1699. Min Range: -10.1699
Max Act: 9.6699. Min Act: -0.1700
Data Index: 8532512 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1699. Min Range: -10.1699
Max Act: 9.6074. Min Act: -0.1700
Data Index: 4112187 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1699. Min Range: -10.1699
Max Act: 9.6074. Min Act: -0.1700
Data Index: 178473 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1699. Min Range: -10.1699
Max Act: 9.6699. Min Act: -0.1700
Data Index: 5167204 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1699. Min Range: -10.1699
Max Act: 9.6074. Min Act: -0.1700
Data Index: 4010602 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #19