Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1905 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8078. Min Range: -6.8078
Max Act: 6.8078. Min Act: -0.1700
Data Index: 5236884 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8078. Min Range: -6.8078
Max Act: 6.7765. Min Act: -0.1700
Data Index: 3259342 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8078. Min Range: -6.8078
Max Act: 6.7453. Min Act: -0.1700
Data Index: 6108821 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8078. Min Range: -6.8078
Max Act: 6.6828. Min Act: -0.1700
Data Index: 1832839 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8078. Min Range: -6.8078
Max Act: 6.6515. Min Act: -0.1700
Data Index: 4713103 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8078. Min Range: -6.8078
Max Act: 6.5578. Min Act: -0.1700
Data Index: 5142247 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8078. Min Range: -6.8078
Max Act: 6.5265. Min Act: -0.1700
Data Index: 3467344 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8078. Min Range: -6.8078
Max Act: 6.5265. Min Act: -0.1700
Data Index: 509709 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8078. Min Range: -6.8078
Max Act: 6.5265. Min Act: -0.1700
Data Index: 5609220 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8078. Min Range: -6.8078
Max Act: 6.4640. Min Act: -0.1700
Data Index: 8056959 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8078. Min Range: -6.8078
Max Act: 6.4328. Min Act: -0.1700
Data Index: 5780063 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8078. Min Range: -6.8078
Max Act: 6.4328. Min Act: -0.1700
Data Index: 4606201 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8078. Min Range: -6.8078
Max Act: 6.4328. Min Act: -0.1700
Data Index: 6460833 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8078. Min Range: -6.8078
Max Act: 6.4328. Min Act: -0.1700
Data Index: 8538042 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8078. Min Range: -6.8078
Max Act: 6.4015. Min Act: -0.1700
Data Index: 7038060 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8078. Min Range: -6.8078
Max Act: 6.4328. Min Act: -0.1700
Data Index: 4520603 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8078. Min Range: -6.8078
Max Act: 6.4015. Min Act: -0.1700
Data Index: 7361473 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8078. Min Range: -6.8078
Max Act: 6.4015. Min Act: -0.1700
Data Index: 1818424 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8078. Min Range: -6.8078
Max Act: 6.4015. Min Act: -0.1700
Data Index: 4272566 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8078. Min Range: -6.8078
Max Act: 6.4015. Min Act: -0.1700
Data Index: 7604695 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #19