Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3301 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6297. Min Range: -4.6297
Max Act: 4.6297. Min Act: -0.1700
Data Index: 7873707 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6297. Min Range: -4.6297
Max Act: 4.6297. Min Act: -0.1700
Data Index: 2809284 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6297. Min Range: -4.6297
Max Act: 4.5985. Min Act: -0.1700
Data Index: 2003831 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6297. Min Range: -4.6297
Max Act: 4.5672. Min Act: -0.1700
Data Index: 1919608 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6297. Min Range: -4.6297
Max Act: 4.5672. Min Act: -0.1700
Data Index: 4214431 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6297. Min Range: -4.6297
Max Act: 4.5047. Min Act: -0.1700
Data Index: 2760750 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6297. Min Range: -4.6297
Max Act: 4.5047. Min Act: -0.1700
Data Index: 1347195 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6297. Min Range: -4.6297
Max Act: 4.5047. Min Act: -0.1700
Data Index: 4124030 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6297. Min Range: -4.6297
Max Act: 4.4735. Min Act: -0.1700
Data Index: 4124029 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6297. Min Range: -4.6297
Max Act: 4.4735. Min Act: -0.1700
Data Index: 5001491 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6297. Min Range: -4.6297
Max Act: 4.4735. Min Act: -0.1700
Data Index: 1253510 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6297. Min Range: -4.6297
Max Act: 4.4735. Min Act: -0.1700
Data Index: 5910191 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6297. Min Range: -4.6297
Max Act: 4.4422. Min Act: -0.1700
Data Index: 6296900 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6297. Min Range: -4.6297
Max Act: 4.5047. Min Act: -0.1700
Data Index: 1432339 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6297. Min Range: -4.6297
Max Act: 4.4735. Min Act: -0.1700
Data Index: 4105560 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6297. Min Range: -4.6297
Max Act: 4.4735. Min Act: -0.1700
Data Index: 3048882 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6297. Min Range: -4.6297
Max Act: 4.4422. Min Act: -0.1700
Data Index: 2902484 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6297. Min Range: -4.6297
Max Act: 4.4422. Min Act: -0.1700
Data Index: 6325884 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6297. Min Range: -4.6297
Max Act: 4.4422. Min Act: -0.1700
Data Index: 6719080 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6297. Min Range: -4.6297
Max Act: 4.4422. Min Act: -0.1700
Data Index: 2642769 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #19