Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2781 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7853. Min Range: -8.7853
Max Act: 8.7853. Min Act: -0.1700
Data Index: 4653217 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7853. Min Range: -8.7853
Max Act: 8.7853. Min Act: -0.1700
Data Index: 5719465 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7853. Min Range: -8.7853
Max Act: 8.5978. Min Act: -0.1700
Data Index: 6122519 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7853. Min Range: -8.7853
Max Act: 8.5978. Min Act: -0.1700
Data Index: 6122518 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7853. Min Range: -8.7853
Max Act: 8.5353. Min Act: -0.1700
Data Index: 5701537 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7853. Min Range: -8.7853
Max Act: 8.5978. Min Act: -0.1700
Data Index: 3814383 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7853. Min Range: -8.7853
Max Act: 8.5353. Min Act: -0.1700
Data Index: 7966142 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7853. Min Range: -8.7853
Max Act: 8.4103. Min Act: -0.1700
Data Index: 7492751 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7853. Min Range: -8.7853
Max Act: 8.3478. Min Act: -0.1700
Data Index: 5025686 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7853. Min Range: -8.7853
Max Act: 8.2853. Min Act: -0.1700
Data Index: 1397132 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7853. Min Range: -8.7853
Max Act: 8.2853. Min Act: -0.1700
Data Index: 2305317 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7853. Min Range: -8.7853
Max Act: 8.2853. Min Act: -0.1700
Data Index: 8478931 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7853. Min Range: -8.7853
Max Act: 8.0978. Min Act: -0.1700
Data Index: 6062097 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7853. Min Range: -8.7853
Max Act: 8.0978. Min Act: -0.1700
Data Index: 2454385 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7853. Min Range: -8.7853
Max Act: 8.0978. Min Act: -0.1700
Data Index: 3971246 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7853. Min Range: -8.7853
Max Act: 8.0353. Min Act: -0.1700
Data Index: 6646971 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7853. Min Range: -8.7853
Max Act: 7.9728. Min Act: -0.1700
Data Index: 6894509 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7853. Min Range: -8.7853
Max Act: 7.9103. Min Act: -0.1700
Data Index: 8624937 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7853. Min Range: -8.7853
Max Act: 7.9103. Min Act: -0.1700
Data Index: 1581870 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7853. Min Range: -8.7853
Max Act: 7.7541. Min Act: -0.1700
Data Index: 7778895 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #19