Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1576 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7447. Min Range: -3.7447
Max Act: 3.7447. Min Act: -0.1700
Data Index: 3426940 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7447. Min Range: -3.7447
Max Act: 3.7447. Min Act: -0.1700
Data Index: 6806985 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7447. Min Range: -3.7447
Max Act: 3.7447. Min Act: -0.1700
Data Index: 5001718 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7447. Min Range: -3.7447
Max Act: 3.7447. Min Act: -0.1700
Data Index: 1766723 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7447. Min Range: -3.7447
Max Act: 3.7134. Min Act: -0.1700
Data Index: 101365 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7447. Min Range: -3.7447
Max Act: 3.7134. Min Act: -0.1700
Data Index: 7272910 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7447. Min Range: -3.7447
Max Act: 3.7134. Min Act: -0.1700
Data Index: 4436880 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7447. Min Range: -3.7447
Max Act: 3.7134. Min Act: -0.1700
Data Index: 3569630 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7447. Min Range: -3.7447
Max Act: 3.7134. Min Act: -0.1700
Data Index: 1331176 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7447. Min Range: -3.7447
Max Act: 3.6821. Min Act: -0.1700
Data Index: 113867 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7447. Min Range: -3.7447
Max Act: 3.6821. Min Act: -0.1700
Data Index: 2192192 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7447. Min Range: -3.7447
Max Act: 3.6821. Min Act: -0.1700
Data Index: 4419021 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7447. Min Range: -3.7447
Max Act: 3.6821. Min Act: -0.1700
Data Index: 1446816 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7447. Min Range: -3.7447
Max Act: 3.6821. Min Act: -0.1700
Data Index: 857996 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7447. Min Range: -3.7447
Max Act: 3.6821. Min Act: -0.1700
Data Index: 5577276 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7447. Min Range: -3.7447
Max Act: 3.6821. Min Act: -0.1700
Data Index: 7443823 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7447. Min Range: -3.7447
Max Act: 3.6821. Min Act: -0.1700
Data Index: 2367227 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7447. Min Range: -3.7447
Max Act: 3.6821. Min Act: -0.1700
Data Index: 2619565 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7447. Min Range: -3.7447
Max Act: 3.6509. Min Act: -0.1700
Data Index: 2290632 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7447. Min Range: -3.7447
Max Act: 3.6509. Min Act: -0.1700
Data Index: 2606044 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #19