Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2968 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2447. Min Range: -6.2447
Max Act: 6.2447. Min Act: -0.1700
Data Index: 712586 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2447. Min Range: -6.2447
Max Act: 5.8697. Min Act: -0.1700
Data Index: 2051723 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2447. Min Range: -6.2447
Max Act: 5.8385. Min Act: -0.1700
Data Index: 8514970 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2447. Min Range: -6.2447
Max Act: 5.8385. Min Act: -0.1700
Data Index: 592447 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2447. Min Range: -6.2447
Max Act: 5.7447. Min Act: -0.1700
Data Index: 909609 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2447. Min Range: -6.2447
Max Act: 5.7760. Min Act: -0.1700
Data Index: 8197677 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2447. Min Range: -6.2447
Max Act: 5.7447. Min Act: -0.1700
Data Index: 5236278 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2447. Min Range: -6.2447
Max Act: 5.7447. Min Act: -0.1700
Data Index: 283548 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2447. Min Range: -6.2447
Max Act: 5.7135. Min Act: -0.1700
Data Index: 4789052 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2447. Min Range: -6.2447
Max Act: 5.6822. Min Act: -0.1700
Data Index: 7476440 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2447. Min Range: -6.2447
Max Act: 5.7447. Min Act: -0.1700
Data Index: 6418573 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2447. Min Range: -6.2447
Max Act: 5.6822. Min Act: -0.1700
Data Index: 1335198 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2447. Min Range: -6.2447
Max Act: 5.6822. Min Act: -0.1700
Data Index: 2061883 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2447. Min Range: -6.2447
Max Act: 5.6822. Min Act: -0.1700
Data Index: 1801601 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2447. Min Range: -6.2447
Max Act: 5.6510. Min Act: -0.1700
Data Index: 6607316 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2447. Min Range: -6.2447
Max Act: 5.6510. Min Act: -0.1700
Data Index: 4535223 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2447. Min Range: -6.2447
Max Act: 5.6197. Min Act: -0.1700
Data Index: 168813 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2447. Min Range: -6.2447
Max Act: 5.6197. Min Act: -0.1700
Data Index: 357533 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2447. Min Range: -6.2447
Max Act: 5.6510. Min Act: -0.1700
Data Index: 3967700 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2447. Min Range: -6.2447
Max Act: 5.6197. Min Act: -0.1700
Data Index: 8149798 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #19