Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1279 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4951. Min Range: -6.4951
Max Act: 6.4951. Min Act: -0.1700
Data Index: 8722676 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4951. Min Range: -6.4951
Max Act: 6.2764. Min Act: -0.1700
Data Index: 7395307 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4951. Min Range: -6.4951
Max Act: 6.2451. Min Act: -0.1700
Data Index: 3207390 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4951. Min Range: -6.4951
Max Act: 6.2139. Min Act: -0.1700
Data Index: 539560 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4951. Min Range: -6.4951
Max Act: 6.1201. Min Act: -0.1700
Data Index: 1661628 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4951. Min Range: -6.4951
Max Act: 6.1514. Min Act: -0.1700
Data Index: 3787212 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4951. Min Range: -6.4951
Max Act: 6.0889. Min Act: -0.1700
Data Index: 4650403 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4951. Min Range: -6.4951
Max Act: 6.0889. Min Act: -0.1700
Data Index: 4783861 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4951. Min Range: -6.4951
Max Act: 6.1201. Min Act: -0.1700
Data Index: 1689698 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4951. Min Range: -6.4951
Max Act: 6.0576. Min Act: -0.1700
Data Index: 4387516 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4951. Min Range: -6.4951
Max Act: 6.0576. Min Act: -0.1700
Data Index: 5204987 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4951. Min Range: -6.4951
Max Act: 6.0264. Min Act: -0.1700
Data Index: 1771241 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4951. Min Range: -6.4951
Max Act: 5.9951. Min Act: -0.1700
Data Index: 2228455 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4951. Min Range: -6.4951
Max Act: 5.9951. Min Act: -0.1700
Data Index: 7657366 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4951. Min Range: -6.4951
Max Act: 5.9951. Min Act: -0.1700
Data Index: 6190544 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4951. Min Range: -6.4951
Max Act: 5.9639. Min Act: -0.1700
Data Index: 6721043 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4951. Min Range: -6.4951
Max Act: 5.9639. Min Act: -0.1700
Data Index: 5051736 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4951. Min Range: -6.4951
Max Act: 5.9639. Min Act: -0.1700
Data Index: 3235004 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4951. Min Range: -6.4951
Max Act: 5.9326. Min Act: -0.1700
Data Index: 7478558 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4951. Min Range: -6.4951
Max Act: 5.9326. Min Act: -0.1700
Data Index: 6889566 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19