Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5838 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0106. Min Range: -8.0106
Max Act: 8.0106. Min Act: -0.1700
Data Index: 2171610 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0106. Min Range: -8.0106
Max Act: 7.8856. Min Act: -0.1700
Data Index: 6922944 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0106. Min Range: -8.0106
Max Act: 7.6044. Min Act: -0.1700
Data Index: 8732580 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0106. Min Range: -8.0106
Max Act: 7.5731. Min Act: -0.1700
Data Index: 2887585 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0106. Min Range: -8.0106
Max Act: 7.4794. Min Act: -0.1700
Data Index: 4612767 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0106. Min Range: -8.0106
Max Act: 7.3231. Min Act: -0.1700
Data Index: 6047733 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0106. Min Range: -8.0106
Max Act: 7.2919. Min Act: -0.1700
Data Index: 1294876 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0106. Min Range: -8.0106
Max Act: 7.1981. Min Act: -0.1700
Data Index: 5893417 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0106. Min Range: -8.0106
Max Act: 7.1981. Min Act: -0.1700
Data Index: 4136631 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0106. Min Range: -8.0106
Max Act: 7.1981. Min Act: -0.1700
Data Index: 1381126 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0106. Min Range: -8.0106
Max Act: 7.1356. Min Act: -0.1700
Data Index: 7881507 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0106. Min Range: -8.0106
Max Act: 7.1356. Min Act: -0.1700
Data Index: 1767070 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0106. Min Range: -8.0106
Max Act: 7.1356. Min Act: -0.1700
Data Index: 6886299 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0106. Min Range: -8.0106
Max Act: 7.1356. Min Act: -0.1700
Data Index: 3246221 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0106. Min Range: -8.0106
Max Act: 7.0731. Min Act: -0.1700
Data Index: 818097 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0106. Min Range: -8.0106
Max Act: 7.0731. Min Act: -0.1700
Data Index: 6976455 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0106. Min Range: -8.0106
Max Act: 7.0731. Min Act: -0.1700
Data Index: 6639849 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0106. Min Range: -8.0106
Max Act: 7.1044. Min Act: -0.1700
Data Index: 3389855 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0106. Min Range: -8.0106
Max Act: 7.0731. Min Act: -0.1700
Data Index: 3354108 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0106. Min Range: -8.0106
Max Act: 7.0419. Min Act: -0.1700
Data Index: 2235784 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19