Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3592 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6361. Min Range: -4.6361
Max Act: 4.6361. Min Act: -0.1700
Data Index: 5573850 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6361. Min Range: -4.6361
Max Act: 4.6049. Min Act: -0.1700
Data Index: 2125864 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6361. Min Range: -4.6361
Max Act: 4.5736. Min Act: -0.1700
Data Index: 6847532 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6361. Min Range: -4.6361
Max Act: 4.5111. Min Act: -0.1700
Data Index: 7566011 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6361. Min Range: -4.6361
Max Act: 4.5111. Min Act: -0.1700
Data Index: 2836349 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6361. Min Range: -4.6361
Max Act: 4.5111. Min Act: -0.1700
Data Index: 1271003 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6361. Min Range: -4.6361
Max Act: 4.5111. Min Act: -0.1700
Data Index: 8135563 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6361. Min Range: -4.6361
Max Act: 4.4799. Min Act: -0.1700
Data Index: 4233747 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6361. Min Range: -4.6361
Max Act: 4.4799. Min Act: -0.1700
Data Index: 1025210 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6361. Min Range: -4.6361
Max Act: 4.4799. Min Act: -0.1700
Data Index: 4474550 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6361. Min Range: -4.6361
Max Act: 4.4486. Min Act: -0.1700
Data Index: 190942 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6361. Min Range: -4.6361
Max Act: 4.4173. Min Act: -0.1700
Data Index: 5771558 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6361. Min Range: -4.6361
Max Act: 4.4173. Min Act: -0.1700
Data Index: 8355783 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6361. Min Range: -4.6361
Max Act: 4.4173. Min Act: -0.1700
Data Index: 1682816 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6361. Min Range: -4.6361
Max Act: 4.4173. Min Act: -0.1700
Data Index: 21666 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6361. Min Range: -4.6361
Max Act: 4.4486. Min Act: -0.1700
Data Index: 885190 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6361. Min Range: -4.6361
Max Act: 4.4486. Min Act: -0.1700
Data Index: 736191 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6361. Min Range: -4.6361
Max Act: 4.4173. Min Act: -0.1700
Data Index: 7409224 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6361. Min Range: -4.6361
Max Act: 4.3861. Min Act: -0.1700
Data Index: 6499063 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6361. Min Range: -4.6361
Max Act: 4.4173. Min Act: -0.1700
Data Index: 4317798 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #19