Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3021 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5598. Min Range: -6.5598
Max Act: 6.5598. Min Act: -0.1700
Data Index: 4373594 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5598. Min Range: -6.5598
Max Act: 6.5285. Min Act: -0.1700
Data Index: 3817666 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5598. Min Range: -6.5598
Max Act: 6.4348. Min Act: -0.1700
Data Index: 5058323 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5598. Min Range: -6.5598
Max Act: 6.2785. Min Act: -0.1700
Data Index: 3817667 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5598. Min Range: -6.5598
Max Act: 6.1848. Min Act: -0.1700
Data Index: 8487852 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5598. Min Range: -6.5598
Max Act: 6.1848. Min Act: -0.1700
Data Index: 3817669 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5598. Min Range: -6.5598
Max Act: 6.1848. Min Act: -0.1700
Data Index: 4373595 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5598. Min Range: -6.5598
Max Act: 6.1223. Min Act: -0.1700
Data Index: 5058324 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5598. Min Range: -6.5598
Max Act: 6.1223. Min Act: -0.1700
Data Index: 3817668 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5598. Min Range: -6.5598
Max Act: 6.0910. Min Act: -0.1700
Data Index: 5219889 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5598. Min Range: -6.5598
Max Act: 6.0598. Min Act: -0.1700
Data Index: 5219888 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5598. Min Range: -6.5598
Max Act: 6.0598. Min Act: -0.1700
Data Index: 1496142 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5598. Min Range: -6.5598
Max Act: 6.0598. Min Act: -0.1700
Data Index: 5128398 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5598. Min Range: -6.5598
Max Act: 5.9660. Min Act: -0.1700
Data Index: 7004003 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5598. Min Range: -6.5598
Max Act: 5.9660. Min Act: -0.1700
Data Index: 4680634 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5598. Min Range: -6.5598
Max Act: 5.9660. Min Act: -0.1700
Data Index: 3395060 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5598. Min Range: -6.5598
Max Act: 5.9348. Min Act: -0.1700
Data Index: 4129825 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5598. Min Range: -6.5598
Max Act: 5.9035. Min Act: -0.1700
Data Index: 6821449 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5598. Min Range: -6.5598
Max Act: 5.9035. Min Act: -0.1700
Data Index: 7410396 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5598. Min Range: -6.5598
Max Act: 5.9035. Min Act: -0.1700
Data Index: 5219887 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #19