Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1044 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.3099. Min Range: -7.3099
Max Act: 7.3099. Min Act: -0.1700
Data Index: 4139111 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3099. Min Range: -7.3099
Max Act: 6.3099. Min Act: -0.1700
Data Index: 6435925 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3099. Min Range: -7.3099
Max Act: 6.3099. Min Act: -0.1700
Data Index: 1175943 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3099. Min Range: -7.3099
Max Act: 6.2474. Min Act: -0.1700
Data Index: 4087946 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3099. Min Range: -7.3099
Max Act: 6.1849. Min Act: -0.1700
Data Index: 3189277 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3099. Min Range: -7.3099
Max Act: 6.1224. Min Act: -0.1700
Data Index: 5810595 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3099. Min Range: -7.3099
Max Act: 6.0287. Min Act: -0.1700
Data Index: 5110241 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3099. Min Range: -7.3099
Max Act: 6.0287. Min Act: -0.1700
Data Index: 8032206 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3099. Min Range: -7.3099
Max Act: 6.0287. Min Act: -0.1700
Data Index: 582235 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3099. Min Range: -7.3099
Max Act: 6.0287. Min Act: -0.1700
Data Index: 2695191 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3099. Min Range: -7.3099
Max Act: 5.9974. Min Act: -0.1700
Data Index: 4135840 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3099. Min Range: -7.3099
Max Act: 5.9974. Min Act: -0.1700
Data Index: 2414848 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3099. Min Range: -7.3099
Max Act: 5.9662. Min Act: -0.1700
Data Index: 7916322 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3099. Min Range: -7.3099
Max Act: 5.9662. Min Act: -0.1700
Data Index: 8086373 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3099. Min Range: -7.3099
Max Act: 5.9037. Min Act: -0.1700
Data Index: 3109148 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3099. Min Range: -7.3099
Max Act: 5.8724. Min Act: -0.1700
Data Index: 3283859 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3099. Min Range: -7.3099
Max Act: 5.9037. Min Act: -0.1700
Data Index: 6899201 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3099. Min Range: -7.3099
Max Act: 5.8724. Min Act: -0.1700
Data Index: 2002255 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3099. Min Range: -7.3099
Max Act: 5.9037. Min Act: -0.1700
Data Index: 852872 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3099. Min Range: -7.3099
Max Act: 5.8724. Min Act: -0.1700
Data Index: 5689856 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #19