Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2694 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7795. Min Range: -4.7795
Max Act: 4.7795. Min Act: -0.1700
Data Index: 4709084 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7795. Min Range: -4.7795
Max Act: 4.7482. Min Act: -0.1700
Data Index: 8199650 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7795. Min Range: -4.7795
Max Act: 4.7482. Min Act: -0.1700
Data Index: 5444277 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7795. Min Range: -4.7795
Max Act: 4.7170. Min Act: -0.1700
Data Index: 4709085 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7795. Min Range: -4.7795
Max Act: 4.6545. Min Act: -0.1700
Data Index: 6045399 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7795. Min Range: -4.7795
Max Act: 4.6545. Min Act: -0.1700
Data Index: 6259355 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7795. Min Range: -4.7795
Max Act: 4.5920. Min Act: -0.1700
Data Index: 5162829 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7795. Min Range: -4.7795
Max Act: 4.5607. Min Act: -0.1700
Data Index: 6499375 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7795. Min Range: -4.7795
Max Act: 4.5607. Min Act: -0.1700
Data Index: 6389249 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7795. Min Range: -4.7795
Max Act: 4.5607. Min Act: -0.1700
Data Index: 1199119 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7795. Min Range: -4.7795
Max Act: 4.5295. Min Act: -0.1700
Data Index: 5584721 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7795. Min Range: -4.7795
Max Act: 4.4982. Min Act: -0.1700
Data Index: 1558131 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7795. Min Range: -4.7795
Max Act: 4.5295. Min Act: -0.1700
Data Index: 3628405 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7795. Min Range: -4.7795
Max Act: 4.5295. Min Act: -0.1700
Data Index: 4740451 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7795. Min Range: -4.7795
Max Act: 4.5295. Min Act: -0.1700
Data Index: 1798913 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7795. Min Range: -4.7795
Max Act: 4.4982. Min Act: -0.1700
Data Index: 5584710 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7795. Min Range: -4.7795
Max Act: 4.4670. Min Act: -0.1700
Data Index: 5584703 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7795. Min Range: -4.7795
Max Act: 4.4982. Min Act: -0.1700
Data Index: 4351138 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7795. Min Range: -4.7795
Max Act: 4.4357. Min Act: -0.1700
Data Index: 5584697 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7795. Min Range: -4.7795
Max Act: 4.4357. Min Act: -0.1700
Data Index: 2930939 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19