Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5010 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.0473. Min Range: -8.0473
Max Act: 8.0473. Min Act: -0.1700
Data Index: 6012736 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0473. Min Range: -8.0473
Max Act: 7.9848. Min Act: -0.1700
Data Index: 8438689 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0473. Min Range: -8.0473
Max Act: 7.7661. Min Act: -0.1700
Data Index: 5312434 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0473. Min Range: -8.0473
Max Act: 7.7036. Min Act: -0.1700
Data Index: 5536236 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0473. Min Range: -8.0473
Max Act: 7.5161. Min Act: -0.1700
Data Index: 3726537 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0473. Min Range: -8.0473
Max Act: 7.5473. Min Act: -0.1700
Data Index: 3963764 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0473. Min Range: -8.0473
Max Act: 7.5161. Min Act: -0.1700
Data Index: 336612 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0473. Min Range: -8.0473
Max Act: 7.3911. Min Act: -0.1700
Data Index: 216127 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0473. Min Range: -8.0473
Max Act: 7.3911. Min Act: -0.1700
Data Index: 4471067 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0473. Min Range: -8.0473
Max Act: 7.2973. Min Act: -0.1700
Data Index: 6218060 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0473. Min Range: -8.0473
Max Act: 7.2973. Min Act: -0.1700
Data Index: 336629 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0473. Min Range: -8.0473
Max Act: 7.2348. Min Act: -0.1700
Data Index: 37203 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0473. Min Range: -8.0473
Max Act: 7.2036. Min Act: -0.1700
Data Index: 2791345 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0473. Min Range: -8.0473
Max Act: 7.2036. Min Act: -0.1700
Data Index: 1169421 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0473. Min Range: -8.0473
Max Act: 7.2036. Min Act: -0.1700
Data Index: 3920930 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0473. Min Range: -8.0473
Max Act: 7.1723. Min Act: -0.1700
Data Index: 3332942 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0473. Min Range: -8.0473
Max Act: 7.1098. Min Act: -0.1700
Data Index: 6241002 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0473. Min Range: -8.0473
Max Act: 7.1098. Min Act: -0.1700
Data Index: 6244536 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0473. Min Range: -8.0473
Max Act: 7.1098. Min Act: -0.1700
Data Index: 5094749 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0473. Min Range: -8.0473
Max Act: 7.1098. Min Act: -0.1700
Data Index: 5038649 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #19