Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1003 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4601. Min Range: -8.4601
Max Act: 8.4601. Min Act: -0.1700
Data Index: 7547043 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4601. Min Range: -8.4601
Max Act: 8.4601. Min Act: -0.1700
Data Index: 1174463 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4601. Min Range: -8.4601
Max Act: 8.1476. Min Act: -0.1700
Data Index: 5213032 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4601. Min Range: -8.4601
Max Act: 7.9601. Min Act: -0.1700
Data Index: 6373299 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4601. Min Range: -8.4601
Max Act: 7.9601. Min Act: -0.1700
Data Index: 458703 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4601. Min Range: -8.4601
Max Act: 7.8976. Min Act: -0.1700
Data Index: 1489407 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4601. Min Range: -8.4601
Max Act: 7.8976. Min Act: -0.1700
Data Index: 6859099 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4601. Min Range: -8.4601
Max Act: 7.8976. Min Act: -0.1700
Data Index: 2246532 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4601. Min Range: -8.4601
Max Act: 7.8351. Min Act: -0.1700
Data Index: 7268630 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4601. Min Range: -8.4601
Max Act: 7.8351. Min Act: -0.1700
Data Index: 2786137 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4601. Min Range: -8.4601
Max Act: 7.7726. Min Act: -0.1700
Data Index: 2177276 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4601. Min Range: -8.4601
Max Act: 7.8351. Min Act: -0.1700
Data Index: 5384957 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4601. Min Range: -8.4601
Max Act: 7.7726. Min Act: -0.1700
Data Index: 735581 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4601. Min Range: -8.4601
Max Act: 7.7726. Min Act: -0.1700
Data Index: 8827741 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4601. Min Range: -8.4601
Max Act: 7.7726. Min Act: -0.1700
Data Index: 5545834 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4601. Min Range: -8.4601
Max Act: 7.7726. Min Act: -0.1700
Data Index: 74893 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4601. Min Range: -8.4601
Max Act: 7.7101. Min Act: -0.1700
Data Index: 7230866 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4601. Min Range: -8.4601
Max Act: 7.7101. Min Act: -0.1700
Data Index: 4382776 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4601. Min Range: -8.4601
Max Act: 7.6476. Min Act: -0.1700
Data Index: 631864 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4601. Min Range: -8.4601
Max Act: 7.6476. Min Act: -0.1700
Data Index: 1944546 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #19