Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4462 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1636. Min Range: -5.1636
Max Act: 5.1636. Min Act: -0.1700
Data Index: 5957952 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1636. Min Range: -5.1636
Max Act: 5.1323. Min Act: -0.1700
Data Index: 6760820 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1636. Min Range: -5.1636
Max Act: 5.0386. Min Act: -0.1700
Data Index: 5190396 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1636. Min Range: -5.1636
Max Act: 4.9448. Min Act: -0.1700
Data Index: 165917 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1636. Min Range: -5.1636
Max Act: 5.0073. Min Act: -0.1700
Data Index: 1831511 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1636. Min Range: -5.1636
Max Act: 4.9761. Min Act: -0.1700
Data Index: 1304861 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1636. Min Range: -5.1636
Max Act: 4.9761. Min Act: -0.1700
Data Index: 3518845 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1636. Min Range: -5.1636
Max Act: 4.9761. Min Act: -0.1700
Data Index: 1184040 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1636. Min Range: -5.1636
Max Act: 4.9761. Min Act: -0.1700
Data Index: 8410660 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1636. Min Range: -5.1636
Max Act: 4.8511. Min Act: -0.1700
Data Index: 8549655 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1636. Min Range: -5.1636
Max Act: 4.8198. Min Act: -0.1700
Data Index: 4829541 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1636. Min Range: -5.1636
Max Act: 4.8511. Min Act: -0.1700
Data Index: 4904506 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1636. Min Range: -5.1636
Max Act: 4.8198. Min Act: -0.1700
Data Index: 6251895 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1636. Min Range: -5.1636
Max Act: 4.7886. Min Act: -0.1700
Data Index: 495515 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1636. Min Range: -5.1636
Max Act: 4.8198. Min Act: -0.1700
Data Index: 5071933 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1636. Min Range: -5.1636
Max Act: 4.8198. Min Act: -0.1700
Data Index: 2967169 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1636. Min Range: -5.1636
Max Act: 4.8198. Min Act: -0.1700
Data Index: 8273279 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1636. Min Range: -5.1636
Max Act: 4.8198. Min Act: -0.1700
Data Index: 8114143 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1636. Min Range: -5.1636
Max Act: 4.8198. Min Act: -0.1700
Data Index: 7102549 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1636. Min Range: -5.1636
Max Act: 4.7886. Min Act: -0.1700
Data Index: 347190 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19