Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2869 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4272. Min Range: -7.4272
Max Act: 7.4272. Min Act: -0.1700
Data Index: 5955728 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4272. Min Range: -7.4272
Max Act: 7.1147. Min Act: -0.1700
Data Index: 3377935 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4272. Min Range: -7.4272
Max Act: 7.1460. Min Act: -0.1700
Data Index: 7173914 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4272. Min Range: -7.4272
Max Act: 7.0835. Min Act: -0.1700
Data Index: 6649212 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4272. Min Range: -7.4272
Max Act: 7.0835. Min Act: -0.1700
Data Index: 902871 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4272. Min Range: -7.4272
Max Act: 7.0210. Min Act: -0.1700
Data Index: 634333 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4272. Min Range: -7.4272
Max Act: 6.9585. Min Act: -0.1700
Data Index: 550768 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4272. Min Range: -7.4272
Max Act: 6.9585. Min Act: -0.1700
Data Index: 1665695 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4272. Min Range: -7.4272
Max Act: 6.8647. Min Act: -0.1700
Data Index: 7712812 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4272. Min Range: -7.4272
Max Act: 6.8647. Min Act: -0.1700
Data Index: 7857689 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4272. Min Range: -7.4272
Max Act: 6.8647. Min Act: -0.1700
Data Index: 6723910 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4272. Min Range: -7.4272
Max Act: 6.8647. Min Act: -0.1700
Data Index: 5397411 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4272. Min Range: -7.4272
Max Act: 6.8335. Min Act: -0.1700
Data Index: 4441566 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4272. Min Range: -7.4272
Max Act: 6.8022. Min Act: -0.1700
Data Index: 7711353 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4272. Min Range: -7.4272
Max Act: 6.7710. Min Act: -0.1700
Data Index: 1138227 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4272. Min Range: -7.4272
Max Act: 6.7710. Min Act: -0.1700
Data Index: 4481487 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4272. Min Range: -7.4272
Max Act: 6.7397. Min Act: -0.1700
Data Index: 6871590 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4272. Min Range: -7.4272
Max Act: 6.7397. Min Act: -0.1700
Data Index: 7802272 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4272. Min Range: -7.4272
Max Act: 6.7397. Min Act: -0.1700
Data Index: 1793722 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4272. Min Range: -7.4272
Max Act: 6.7085. Min Act: -0.1700
Data Index: 1928646 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19