Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2763 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4309. Min Range: -7.4309
Max Act: 7.4309. Min Act: -0.1700
Data Index: 6458933 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4309. Min Range: -7.4309
Max Act: 7.2747. Min Act: -0.1700
Data Index: 5770216 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4309. Min Range: -7.4309
Max Act: 7.2122. Min Act: -0.1700
Data Index: 3383139 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4309. Min Range: -7.4309
Max Act: 7.1809. Min Act: -0.1700
Data Index: 3858110 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4309. Min Range: -7.4309
Max Act: 7.1809. Min Act: -0.1700
Data Index: 4666326 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4309. Min Range: -7.4309
Max Act: 7.1184. Min Act: -0.1700
Data Index: 6133943 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4309. Min Range: -7.4309
Max Act: 7.1497. Min Act: -0.1700
Data Index: 289581 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4309. Min Range: -7.4309
Max Act: 7.0872. Min Act: -0.1700
Data Index: 5482443 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4309. Min Range: -7.4309
Max Act: 7.0559. Min Act: -0.1700
Data Index: 106389 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4309. Min Range: -7.4309
Max Act: 7.0247. Min Act: -0.1700
Data Index: 7639256 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4309. Min Range: -7.4309
Max Act: 6.9622. Min Act: -0.1700
Data Index: 3622081 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4309. Min Range: -7.4309
Max Act: 6.9622. Min Act: -0.1700
Data Index: 6052385 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4309. Min Range: -7.4309
Max Act: 6.8997. Min Act: -0.1700
Data Index: 5123173 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4309. Min Range: -7.4309
Max Act: 6.8684. Min Act: -0.1700
Data Index: 8174011 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4309. Min Range: -7.4309
Max Act: 6.7434. Min Act: -0.1700
Data Index: 4779727 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4309. Min Range: -7.4309
Max Act: 6.7434. Min Act: -0.1700
Data Index: 2160274 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4309. Min Range: -7.4309
Max Act: 6.7122. Min Act: -0.1700
Data Index: 6133944 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4309. Min Range: -7.4309
Max Act: 6.7122. Min Act: -0.1700
Data Index: 762220 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4309. Min Range: -7.4309
Max Act: 6.7122. Min Act: -0.1700
Data Index: 504175 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4309. Min Range: -7.4309
Max Act: 6.6497. Min Act: -0.1700
Data Index: 4341858 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #19