Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4042 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5016. Min Range: -5.5016
Max Act: 5.5016. Min Act: -0.1700
Data Index: 3567356 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5016. Min Range: -5.5016
Max Act: 5.4704. Min Act: -0.1700
Data Index: 3711769 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5016. Min Range: -5.5016
Max Act: 5.3766. Min Act: -0.1700
Data Index: 2150710 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5016. Min Range: -5.5016
Max Act: 5.3454. Min Act: -0.1700
Data Index: 2903716 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5016. Min Range: -5.5016
Max Act: 5.3141. Min Act: -0.1700
Data Index: 6589895 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5016. Min Range: -5.5016
Max Act: 5.2829. Min Act: -0.1700
Data Index: 1366307 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5016. Min Range: -5.5016
Max Act: 5.3141. Min Act: -0.1700
Data Index: 646951 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5016. Min Range: -5.5016
Max Act: 5.2204. Min Act: -0.1700
Data Index: 3952804 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5016. Min Range: -5.5016
Max Act: 5.3141. Min Act: -0.1700
Data Index: 8004345 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5016. Min Range: -5.5016
Max Act: 5.2829. Min Act: -0.1700
Data Index: 5835142 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5016. Min Range: -5.5016
Max Act: 5.3141. Min Act: -0.1700
Data Index: 1428087 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5016. Min Range: -5.5016
Max Act: 5.2516. Min Act: -0.1700
Data Index: 2008118 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5016. Min Range: -5.5016
Max Act: 5.2829. Min Act: -0.1700
Data Index: 7804249 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5016. Min Range: -5.5016
Max Act: 5.2204. Min Act: -0.1700
Data Index: 8228043 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5016. Min Range: -5.5016
Max Act: 5.2204. Min Act: -0.1700
Data Index: 1189947 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5016. Min Range: -5.5016
Max Act: 5.2516. Min Act: -0.1700
Data Index: 8500053 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5016. Min Range: -5.5016
Max Act: 5.2204. Min Act: -0.1700
Data Index: 5107022 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5016. Min Range: -5.5016
Max Act: 5.2204. Min Act: -0.1700
Data Index: 7079641 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5016. Min Range: -5.5016
Max Act: 5.1891. Min Act: -0.1700
Data Index: 8170773 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5016. Min Range: -5.5016
Max Act: 5.1579. Min Act: -0.1700
Data Index: 6433497 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #19