Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3357 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8045. Min Range: -6.8045
Max Act: 6.8045. Min Act: -0.1700
Data Index: 3986705 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8045. Min Range: -6.8045
Max Act: 6.8045. Min Act: -0.1700
Data Index: 5547226 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8045. Min Range: -6.8045
Max Act: 6.8045. Min Act: -0.1700
Data Index: 4815740 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8045. Min Range: -6.8045
Max Act: 6.7733. Min Act: -0.1700
Data Index: 2536592 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8045. Min Range: -6.8045
Max Act: 6.7420. Min Act: -0.1700
Data Index: 5889500 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8045. Min Range: -6.8045
Max Act: 6.6483. Min Act: -0.1700
Data Index: 7403844 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8045. Min Range: -6.8045
Max Act: 6.5545. Min Act: -0.1700
Data Index: 3208023 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8045. Min Range: -6.8045
Max Act: 6.5233. Min Act: -0.1700
Data Index: 3610910 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8045. Min Range: -6.8045
Max Act: 6.4920. Min Act: -0.1700
Data Index: 7292981 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8045. Min Range: -6.8045
Max Act: 6.4920. Min Act: -0.1700
Data Index: 8631050 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8045. Min Range: -6.8045
Max Act: 6.4608. Min Act: -0.1700
Data Index: 5974888 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8045. Min Range: -6.8045
Max Act: 6.4295. Min Act: -0.1700
Data Index: 2755000 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8045. Min Range: -6.8045
Max Act: 6.4608. Min Act: -0.1700
Data Index: 897656 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8045. Min Range: -6.8045
Max Act: 6.4608. Min Act: -0.1700
Data Index: 3664481 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8045. Min Range: -6.8045
Max Act: 6.4608. Min Act: -0.1700
Data Index: 4025927 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8045. Min Range: -6.8045
Max Act: 6.4608. Min Act: -0.1700
Data Index: 8719314 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8045. Min Range: -6.8045
Max Act: 6.4295. Min Act: -0.1700
Data Index: 7131293 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8045. Min Range: -6.8045
Max Act: 6.4295. Min Act: -0.1700
Data Index: 4569785 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8045. Min Range: -6.8045
Max Act: 6.4295. Min Act: -0.1700
Data Index: 2631294 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8045. Min Range: -6.8045
Max Act: 6.4295. Min Act: -0.1700
Data Index: 1834279 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #19