Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 64 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1348. Min Range: -7.1348
Max Act: 7.1348. Min Act: -0.1699
Data Index: 8515686 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1348. Min Range: -7.1348
Max Act: 7.1348. Min Act: -0.1700
Data Index: 4111164 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1348. Min Range: -7.1348
Max Act: 7.0723. Min Act: -0.1699
Data Index: 5915025 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1348. Min Range: -7.1348
Max Act: 7.0723. Min Act: -0.1700
Data Index: 1466530 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1348. Min Range: -7.1348
Max Act: 7.0723. Min Act: -0.1700
Data Index: 1284037 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1348. Min Range: -7.1348
Max Act: 7.0723. Min Act: -0.1700
Data Index: 334172 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1348. Min Range: -7.1348
Max Act: 7.0098. Min Act: -0.1700
Data Index: 2091232 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1348. Min Range: -7.1348
Max Act: 7.0098. Min Act: -0.1700
Data Index: 2175812 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1348. Min Range: -7.1348
Max Act: 7.0098. Min Act: -0.1700
Data Index: 2458300 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1348. Min Range: -7.1348
Max Act: 7.0098. Min Act: -0.1700
Data Index: 2902338 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1348. Min Range: -7.1348
Max Act: 7.0098. Min Act: -0.1700
Data Index: 3642835 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1348. Min Range: -7.1348
Max Act: 7.0098. Min Act: -0.1681
Data Index: 3804591 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1348. Min Range: -7.1348
Max Act: 7.0098. Min Act: -0.1700
Data Index: 4069579 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1348. Min Range: -7.1348
Max Act: 7.0098. Min Act: -0.1654
Data Index: 44514 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1348. Min Range: -7.1348
Max Act: 7.0098. Min Act: -0.1697
Data Index: 615049 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1348. Min Range: -7.1348
Max Act: 7.0098. Min Act: -0.1700
Data Index: 1637877 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1348. Min Range: -7.1348
Max Act: 7.0098. Min Act: -0.1700
Data Index: 4209285 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1348. Min Range: -7.1348
Max Act: 7.0098. Min Act: -0.1698
Data Index: 4590775 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1348. Min Range: -7.1348
Max Act: 7.0098. Min Act: -0.1699
Data Index: 5849477 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1348. Min Range: -7.1348
Max Act: 7.0098. Min Act: -0.1700
Data Index: 1603499 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19