Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 19 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.2306. Min Range: -8.2306
Max Act: 8.2306. Min Act: -0.1700
Data Index: 3519984 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2306. Min Range: -8.2306
Max Act: 8.2306. Min Act: -0.1700
Data Index: 1614818 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2306. Min Range: -8.2306
Max Act: 7.9806. Min Act: -0.1700
Data Index: 571145 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2306. Min Range: -8.2306
Max Act: 8.0431. Min Act: -0.1700
Data Index: 5924054 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2306. Min Range: -8.2306
Max Act: 7.9806. Min Act: -0.1700
Data Index: 8486069 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2306. Min Range: -8.2306
Max Act: 7.9181. Min Act: -0.1700
Data Index: 5065353 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2306. Min Range: -8.2306
Max Act: 7.9181. Min Act: -0.1700
Data Index: 1606492 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2306. Min Range: -8.2306
Max Act: 7.9181. Min Act: -0.1700
Data Index: 5822600 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2306. Min Range: -8.2306
Max Act: 7.8244. Min Act: -0.1700
Data Index: 7760391 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2306. Min Range: -8.2306
Max Act: 7.8244. Min Act: -0.1700
Data Index: 8459138 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2306. Min Range: -8.2306
Max Act: 7.7619. Min Act: -0.1700
Data Index: 2999159 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2306. Min Range: -8.2306
Max Act: 7.7619. Min Act: -0.1700
Data Index: 2118185 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2306. Min Range: -8.2306
Max Act: 7.7306. Min Act: -0.1700
Data Index: 2884109 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2306. Min Range: -8.2306
Max Act: 7.7306. Min Act: -0.1700
Data Index: 8178582 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2306. Min Range: -8.2306
Max Act: 7.7619. Min Act: -0.1700
Data Index: 7754170 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2306. Min Range: -8.2306
Max Act: 7.6994. Min Act: -0.1700
Data Index: 3068472 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2306. Min Range: -8.2306
Max Act: 7.6994. Min Act: -0.1700
Data Index: 1647218 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2306. Min Range: -8.2306
Max Act: 7.6369. Min Act: -0.1700
Data Index: 7092910 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2306. Min Range: -8.2306
Max Act: 7.6369. Min Act: -0.1700
Data Index: 2695073 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2306. Min Range: -8.2306
Max Act: 7.6369. Min Act: -0.1700
Data Index: 7233039 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19