Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2250 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.5926. Min Range: -1.5926
Max Act: 1.5926. Min Act: -0.1700
Data Index: 3036697 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5926. Min Range: -1.5926
Max Act: 1.5576. Min Act: -0.1700
Data Index: 8741217 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5926. Min Range: -1.5926
Max Act: 1.5401. Min Act: -0.1700
Data Index: 8042197 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5926. Min Range: -1.5926
Max Act: 1.5051. Min Act: -0.1700
Data Index: 1904555 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5926. Min Range: -1.5926
Max Act: 1.5226. Min Act: -0.1700
Data Index: 6171685 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5926. Min Range: -1.5926
Max Act: 1.5051. Min Act: -0.1700
Data Index: 7505050 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5926. Min Range: -1.5926
Max Act: 1.5051. Min Act: -0.1700
Data Index: 2340754 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5926. Min Range: -1.5926
Max Act: 1.4699. Min Act: -0.1700
Data Index: 8198422 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5926. Min Range: -1.5926
Max Act: 1.4699. Min Act: -0.1700
Data Index: 1267147 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5926. Min Range: -1.5926
Max Act: 1.4523. Min Act: -0.1700
Data Index: 1381645 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5926. Min Range: -1.5926
Max Act: 1.4699. Min Act: -0.1700
Data Index: 6189705 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5926. Min Range: -1.5926
Max Act: 1.4699. Min Act: -0.1700
Data Index: 7981944 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5926. Min Range: -1.5926
Max Act: 1.4699. Min Act: -0.1700
Data Index: 3870731 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5926. Min Range: -1.5926
Max Act: 1.4699. Min Act: -0.1700
Data Index: 8661768 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5926. Min Range: -1.5926
Max Act: 1.4699. Min Act: -0.1700
Data Index: 2615534 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5926. Min Range: -1.5926
Max Act: 1.4523. Min Act: -0.1700
Data Index: 1734674 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5926. Min Range: -1.5926
Max Act: 1.4523. Min Act: -0.1700
Data Index: 5659796 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5926. Min Range: -1.5926
Max Act: 1.4699. Min Act: -0.1700
Data Index: 1972532 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5926. Min Range: -1.5926
Max Act: 1.4523. Min Act: -0.1700
Data Index: 7200471 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5926. Min Range: -1.5926
Max Act: 1.4523. Min Act: -0.1700
Data Index: 11723 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #19