Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3707 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 15.4885. Min Range: -15.4885
Max Act: 15.4885. Min Act: -0.1700
Data Index: 7151783 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 15.4885. Min Range: -15.4885
Max Act: 14.9260. Min Act: -0.1700
Data Index: 7919514 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 15.4885. Min Range: -15.4885
Max Act: 14.1760. Min Act: -0.1700
Data Index: 643013 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 15.4885. Min Range: -15.4885
Max Act: 14.0510. Min Act: -0.1700
Data Index: 7344087 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 15.4885. Min Range: -15.4885
Max Act: 13.9885. Min Act: -0.1700
Data Index: 8205257 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 15.4885. Min Range: -15.4885
Max Act: 13.9260. Min Act: -0.1700
Data Index: 520870 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 15.4885. Min Range: -15.4885
Max Act: 13.9260. Min Act: -0.1700
Data Index: 1722220 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 15.4885. Min Range: -15.4885
Max Act: 13.8635. Min Act: -0.1700
Data Index: 3388475 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 15.4885. Min Range: -15.4885
Max Act: 13.6760. Min Act: -0.1700
Data Index: 1548362 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 15.4885. Min Range: -15.4885
Max Act: 13.5510. Min Act: -0.1700
Data Index: 1101567 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 15.4885. Min Range: -15.4885
Max Act: 13.5510. Min Act: -0.1700
Data Index: 7212079 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 15.4885. Min Range: -15.4885
Max Act: 13.6135. Min Act: -0.1700
Data Index: 5189096 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 15.4885. Min Range: -15.4885
Max Act: 13.4885. Min Act: -0.1700
Data Index: 5889253 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 15.4885. Min Range: -15.4885
Max Act: 13.4885. Min Act: -0.1700
Data Index: 3108836 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 15.4885. Min Range: -15.4885
Max Act: 13.4885. Min Act: -0.1700
Data Index: 6110329 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 15.4885. Min Range: -15.4885
Max Act: 13.4260. Min Act: -0.1700
Data Index: 1118693 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 15.4885. Min Range: -15.4885
Max Act: 13.3635. Min Act: -0.1700
Data Index: 4063298 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 15.4885. Min Range: -15.4885
Max Act: 13.3635. Min Act: -0.1700
Data Index: 4251770 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 15.4885. Min Range: -15.4885
Max Act: 13.3635. Min Act: -0.1700
Data Index: 2162574 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 15.4885. Min Range: -15.4885
Max Act: 13.3635. Min Act: -0.1700
Data Index: 1620802 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #19