Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1773 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3797. Min Range: -6.3797
Max Act: 6.3797. Min Act: -0.1700
Data Index: 2291245 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3797. Min Range: -6.3797
Max Act: 6.3485. Min Act: -0.1700
Data Index: 1021725 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3797. Min Range: -6.3797
Max Act: 6.2860. Min Act: -0.1700
Data Index: 3227692 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3797. Min Range: -6.3797
Max Act: 6.1297. Min Act: -0.1700
Data Index: 165419 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3797. Min Range: -6.3797
Max Act: 6.0985. Min Act: -0.1700
Data Index: 5800132 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3797. Min Range: -6.3797
Max Act: 6.1297. Min Act: -0.1700
Data Index: 6077723 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3797. Min Range: -6.3797
Max Act: 6.0985. Min Act: -0.1700
Data Index: 680897 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3797. Min Range: -6.3797
Max Act: 6.0985. Min Act: -0.1700
Data Index: 3346564 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3797. Min Range: -6.3797
Max Act: 6.0360. Min Act: -0.1700
Data Index: 1126909 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3797. Min Range: -6.3797
Max Act: 6.0360. Min Act: -0.1700
Data Index: 6276470 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3797. Min Range: -6.3797
Max Act: 6.0360. Min Act: -0.1700
Data Index: 6776698 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3797. Min Range: -6.3797
Max Act: 6.0360. Min Act: -0.1700
Data Index: 5059451 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3797. Min Range: -6.3797
Max Act: 6.0047. Min Act: -0.1700
Data Index: 1849232 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3797. Min Range: -6.3797
Max Act: 6.0047. Min Act: -0.1700
Data Index: 3363146 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3797. Min Range: -6.3797
Max Act: 5.9735. Min Act: -0.1700
Data Index: 3039519 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3797. Min Range: -6.3797
Max Act: 6.0047. Min Act: -0.1700
Data Index: 8577390 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3797. Min Range: -6.3797
Max Act: 6.0047. Min Act: -0.1700
Data Index: 7961698 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3797. Min Range: -6.3797
Max Act: 6.0047. Min Act: -0.1700
Data Index: 2623430 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3797. Min Range: -6.3797
Max Act: 5.9735. Min Act: -0.1700
Data Index: 1674189 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3797. Min Range: -6.3797
Max Act: 5.9735. Min Act: -0.1700
Data Index: 2678303 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #19