Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3562 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9079. Min Range: -3.9079
Max Act: 3.9079. Min Act: -0.1700
Data Index: 6307323 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9079. Min Range: -3.9079
Max Act: 3.8767. Min Act: -0.1700
Data Index: 8121000 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9079. Min Range: -3.9079
Max Act: 3.8141. Min Act: -0.1700
Data Index: 6150710 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9079. Min Range: -3.9079
Max Act: 3.7516. Min Act: -0.1700
Data Index: 7021856 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9079. Min Range: -3.9079
Max Act: 3.7203. Min Act: -0.1700
Data Index: 6289888 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9079. Min Range: -3.9079
Max Act: 3.6890. Min Act: -0.1700
Data Index: 6047931 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9079. Min Range: -3.9079
Max Act: 3.6264. Min Act: -0.1700
Data Index: 4384377 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9079. Min Range: -3.9079
Max Act: 3.5951. Min Act: -0.1700
Data Index: 4106264 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9079. Min Range: -3.9079
Max Act: 3.5638. Min Act: -0.1700
Data Index: 3221279 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9079. Min Range: -3.9079
Max Act: 3.5012. Min Act: -0.1700
Data Index: 7950207 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9079. Min Range: -3.9079
Max Act: 3.5325. Min Act: -0.1700
Data Index: 5082898 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9079. Min Range: -3.9079
Max Act: 3.5325. Min Act: -0.1700
Data Index: 1234578 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9079. Min Range: -3.9079
Max Act: 3.5325. Min Act: -0.1700
Data Index: 7808156 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9079. Min Range: -3.9079
Max Act: 3.5012. Min Act: -0.1700
Data Index: 2510225 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9079. Min Range: -3.9079
Max Act: 3.5012. Min Act: -0.1700
Data Index: 1323116 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9079. Min Range: -3.9079
Max Act: 3.5012. Min Act: -0.1700
Data Index: 5739304 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9079. Min Range: -3.9079
Max Act: 3.5012. Min Act: -0.1700
Data Index: 4190941 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9079. Min Range: -3.9079
Max Act: 3.4699. Min Act: -0.1700
Data Index: 5226015 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9079. Min Range: -3.9079
Max Act: 3.4542. Min Act: -0.1700
Data Index: 1488022 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9079. Min Range: -3.9079
Max Act: 3.4385. Min Act: -0.1700
Data Index: 7288395 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #19