Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1802 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7497. Min Range: -5.7497
Max Act: 5.7497. Min Act: -0.1700
Data Index: 760881 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7497. Min Range: -5.7497
Max Act: 5.6247. Min Act: -0.1700
Data Index: 1363174 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7497. Min Range: -5.7497
Max Act: 5.5935. Min Act: -0.1700
Data Index: 4515743 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7497. Min Range: -5.7497
Max Act: 5.5622. Min Act: -0.1700
Data Index: 5426415 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7497. Min Range: -5.7497
Max Act: 5.5622. Min Act: -0.1700
Data Index: 3008520 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7497. Min Range: -5.7497
Max Act: 5.5310. Min Act: -0.1700
Data Index: 7774800 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7497. Min Range: -5.7497
Max Act: 5.4997. Min Act: -0.1700
Data Index: 4651732 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7497. Min Range: -5.7497
Max Act: 5.4997. Min Act: -0.1700
Data Index: 3719949 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7497. Min Range: -5.7497
Max Act: 5.4685. Min Act: -0.1700
Data Index: 7564940 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7497. Min Range: -5.7497
Max Act: 5.4685. Min Act: -0.1700
Data Index: 5958428 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7497. Min Range: -5.7497
Max Act: 5.4372. Min Act: -0.1700
Data Index: 7767694 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7497. Min Range: -5.7497
Max Act: 5.4372. Min Act: -0.1700
Data Index: 6574143 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7497. Min Range: -5.7497
Max Act: 5.4372. Min Act: -0.1700
Data Index: 6942734 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7497. Min Range: -5.7497
Max Act: 5.4372. Min Act: -0.1700
Data Index: 57136 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7497. Min Range: -5.7497
Max Act: 5.4060. Min Act: -0.1700
Data Index: 943902 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7497. Min Range: -5.7497
Max Act: 5.4060. Min Act: -0.1700
Data Index: 3970847 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7497. Min Range: -5.7497
Max Act: 5.4060. Min Act: -0.1700
Data Index: 908675 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7497. Min Range: -5.7497
Max Act: 5.4060. Min Act: -0.1700
Data Index: 5953998 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7497. Min Range: -5.7497
Max Act: 5.4060. Min Act: -0.1700
Data Index: 4990696 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7497. Min Range: -5.7497
Max Act: 5.4060. Min Act: -0.1700
Data Index: 1224931 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #19