Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4748 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.8284. Min Act: -0.1700
Data Index: 5452964 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.7346. Min Act: -0.1700
Data Index: 2703486 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.6721. Min Act: -0.1700
Data Index: 12306 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.6721. Min Act: -0.1700
Data Index: 7847066 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.6721. Min Act: -0.1700
Data Index: 4190983 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.6721. Min Act: -0.1700
Data Index: 897126 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.6409. Min Act: -0.1700
Data Index: 2603383 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.6409. Min Act: -0.1700
Data Index: 4880679 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.6096. Min Act: -0.1700
Data Index: 2074522 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.6096. Min Act: -0.1700
Data Index: 8603414 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.6096. Min Act: -0.1700
Data Index: 8456213 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.5784. Min Act: -0.1700
Data Index: 464138 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.6096. Min Act: -0.1700
Data Index: 607459 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.5471. Min Act: -0.1700
Data Index: 8696654 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.5471. Min Act: -0.1700
Data Index: 4358249 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.5471. Min Act: -0.1700
Data Index: 2855658 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.5159. Min Act: -0.1700
Data Index: 3242910 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.5159. Min Act: -0.1700
Data Index: 6280519 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.5159. Min Act: -0.1700
Data Index: 7616654 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.4846. Min Act: -0.1700
Data Index: 8680371 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #19