Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2874 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.7265. Min Range: -7.7265
Max Act: 7.7265. Min Act: -0.1700
Data Index: 5875289 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7265. Min Range: -7.7265
Max Act: 7.4453. Min Act: -0.1700
Data Index: 8309848 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7265. Min Range: -7.7265
Max Act: 7.3828. Min Act: -0.1700
Data Index: 7405741 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7265. Min Range: -7.7265
Max Act: 7.3828. Min Act: -0.1700
Data Index: 7405743 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7265. Min Range: -7.7265
Max Act: 7.2265. Min Act: -0.1700
Data Index: 1121612 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7265. Min Range: -7.7265
Max Act: 7.0390. Min Act: -0.1700
Data Index: 3897787 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7265. Min Range: -7.7265
Max Act: 6.9453. Min Act: -0.1700
Data Index: 7401455 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7265. Min Range: -7.7265
Max Act: 6.7890. Min Act: -0.1700
Data Index: 8254521 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7265. Min Range: -7.7265
Max Act: 6.8515. Min Act: -0.1700
Data Index: 7797746 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7265. Min Range: -7.7265
Max Act: 6.8203. Min Act: -0.1700
Data Index: 4047926 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7265. Min Range: -7.7265
Max Act: 6.7890. Min Act: -0.1700
Data Index: 3559905 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7265. Min Range: -7.7265
Max Act: 6.7578. Min Act: -0.1700
Data Index: 1121151 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7265. Min Range: -7.7265
Max Act: 6.6640. Min Act: -0.1700
Data Index: 6893009 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7265. Min Range: -7.7265
Max Act: 6.6640. Min Act: -0.1700
Data Index: 510274 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7265. Min Range: -7.7265
Max Act: 6.6640. Min Act: -0.1700
Data Index: 34587 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7265. Min Range: -7.7265
Max Act: 6.6328. Min Act: -0.1700
Data Index: 3475044 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7265. Min Range: -7.7265
Max Act: 6.6328. Min Act: -0.1700
Data Index: 640996 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7265. Min Range: -7.7265
Max Act: 6.6640. Min Act: -0.1700
Data Index: 3456650 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7265. Min Range: -7.7265
Max Act: 6.6328. Min Act: -0.1700
Data Index: 6454825 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7265. Min Range: -7.7265
Max Act: 6.6015. Min Act: -0.1700
Data Index: 3715313 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #19