Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6346 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9349. Min Range: -5.9349
Max Act: 5.9349. Min Act: -0.1700
Data Index: 4874903 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9349. Min Range: -5.9349
Max Act: 5.9349. Min Act: -0.1700
Data Index: 5102162 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9349. Min Range: -5.9349
Max Act: 5.9036. Min Act: -0.1700
Data Index: 1557759 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9349. Min Range: -5.9349
Max Act: 5.8724. Min Act: -0.1700
Data Index: 1113580 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9349. Min Range: -5.9349
Max Act: 5.8724. Min Act: -0.1700
Data Index: 7174121 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9349. Min Range: -5.9349
Max Act: 5.8411. Min Act: -0.1700
Data Index: 1167418 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9349. Min Range: -5.9349
Max Act: 5.8411. Min Act: -0.1700
Data Index: 4601550 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9349. Min Range: -5.9349
Max Act: 5.8099. Min Act: -0.1700
Data Index: 4175950 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9349. Min Range: -5.9349
Max Act: 5.7786. Min Act: -0.1700
Data Index: 6533840 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9349. Min Range: -5.9349
Max Act: 5.7474. Min Act: -0.1700
Data Index: 6372156 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9349. Min Range: -5.9349
Max Act: 5.6849. Min Act: -0.1700
Data Index: 2475665 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9349. Min Range: -5.9349
Max Act: 5.6849. Min Act: -0.1700
Data Index: 8246217 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9349. Min Range: -5.9349
Max Act: 5.6536. Min Act: -0.1700
Data Index: 6299551 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9349. Min Range: -5.9349
Max Act: 5.6536. Min Act: -0.1700
Data Index: 5047435 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9349. Min Range: -5.9349
Max Act: 5.6536. Min Act: -0.1700
Data Index: 2617963 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9349. Min Range: -5.9349
Max Act: 5.6224. Min Act: -0.1700
Data Index: 3655061 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9349. Min Range: -5.9349
Max Act: 5.6224. Min Act: -0.1700
Data Index: 7140331 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9349. Min Range: -5.9349
Max Act: 5.6224. Min Act: -0.1700
Data Index: 8365598 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9349. Min Range: -5.9349
Max Act: 5.6224. Min Act: -0.1700
Data Index: 2328106 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9349. Min Range: -5.9349
Max Act: 5.5911. Min Act: -0.1700
Data Index: 2577553 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #19