Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3856 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4026. Min Range: -4.4026
Max Act: 4.4026. Min Act: -0.1700
Data Index: 2723715 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4026. Min Range: -4.4026
Max Act: 4.4026. Min Act: -0.1700
Data Index: 67071 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4026. Min Range: -4.4026
Max Act: 4.3713. Min Act: -0.1700
Data Index: 1981315 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4026. Min Range: -4.4026
Max Act: 4.4026. Min Act: -0.1700
Data Index: 6276434 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4026. Min Range: -4.4026
Max Act: 4.3088. Min Act: -0.1700
Data Index: 1036822 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4026. Min Range: -4.4026
Max Act: 4.3088. Min Act: -0.1700
Data Index: 665538 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4026. Min Range: -4.4026
Max Act: 4.3088. Min Act: -0.1700
Data Index: 1981313 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4026. Min Range: -4.4026
Max Act: 4.3088. Min Act: -0.1700
Data Index: 7393196 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4026. Min Range: -4.4026
Max Act: 4.2776. Min Act: -0.1700
Data Index: 6790304 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4026. Min Range: -4.4026
Max Act: 4.3088. Min Act: -0.1700
Data Index: 8666008 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4026. Min Range: -4.4026
Max Act: 4.3088. Min Act: -0.1700
Data Index: 3516699 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4026. Min Range: -4.4026
Max Act: 4.2776. Min Act: -0.1700
Data Index: 595385 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4026. Min Range: -4.4026
Max Act: 4.2776. Min Act: -0.1700
Data Index: 4355981 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4026. Min Range: -4.4026
Max Act: 4.2776. Min Act: -0.1700
Data Index: 6025452 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4026. Min Range: -4.4026
Max Act: 4.2776. Min Act: -0.1700
Data Index: 719254 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4026. Min Range: -4.4026
Max Act: 4.2463. Min Act: -0.1700
Data Index: 5937648 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4026. Min Range: -4.4026
Max Act: 4.2776. Min Act: -0.1700
Data Index: 3138660 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4026. Min Range: -4.4026
Max Act: 4.2463. Min Act: -0.1700
Data Index: 1730009 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4026. Min Range: -4.4026
Max Act: 4.2463. Min Act: -0.1700
Data Index: 3761673 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4026. Min Range: -4.4026
Max Act: 4.2776. Min Act: -0.1700
Data Index: 3232586 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #19