Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3982 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7513. Min Range: -7.7513
Max Act: 7.7513. Min Act: -0.1700
Data Index: 3961567 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7513. Min Range: -7.7513
Max Act: 7.6888. Min Act: -0.1700
Data Index: 4439010 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7513. Min Range: -7.7513
Max Act: 7.6888. Min Act: -0.1700
Data Index: 1012806 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7513. Min Range: -7.7513
Max Act: 7.6888. Min Act: -0.1700
Data Index: 8474866 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7513. Min Range: -7.7513
Max Act: 7.6576. Min Act: -0.1700
Data Index: 6178800 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7513. Min Range: -7.7513
Max Act: 7.6263. Min Act: -0.1700
Data Index: 7502923 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7513. Min Range: -7.7513
Max Act: 7.5638. Min Act: -0.1700
Data Index: 1195085 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7513. Min Range: -7.7513
Max Act: 7.5951. Min Act: -0.1700
Data Index: 2308422 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7513. Min Range: -7.7513
Max Act: 7.5326. Min Act: -0.1700
Data Index: 8296028 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7513. Min Range: -7.7513
Max Act: 7.5326. Min Act: -0.1700
Data Index: 4436 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7513. Min Range: -7.7513
Max Act: 7.4701. Min Act: -0.1700
Data Index: 4363699 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7513. Min Range: -7.7513
Max Act: 7.4388. Min Act: -0.1700
Data Index: 6555253 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7513. Min Range: -7.7513
Max Act: 7.4388. Min Act: -0.1700
Data Index: 3747441 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7513. Min Range: -7.7513
Max Act: 7.4701. Min Act: -0.1700
Data Index: 8514287 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7513. Min Range: -7.7513
Max Act: 7.4076. Min Act: -0.1700
Data Index: 3969029 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7513. Min Range: -7.7513
Max Act: 7.4076. Min Act: -0.1700
Data Index: 6907723 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7513. Min Range: -7.7513
Max Act: 7.3763. Min Act: -0.1700
Data Index: 1197083 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7513. Min Range: -7.7513
Max Act: 7.4076. Min Act: -0.1700
Data Index: 344374 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7513. Min Range: -7.7513
Max Act: 7.4076. Min Act: -0.1700
Data Index: 1984759 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7513. Min Range: -7.7513
Max Act: 7.4076. Min Act: -0.1700
Data Index: 579535 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #19