Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3643 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4456. Min Range: -4.4456
Max Act: 4.4456. Min Act: -0.1700
Data Index: 7880349 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4456. Min Range: -4.4456
Max Act: 4.3519. Min Act: -0.1700
Data Index: 5171813 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4456. Min Range: -4.4456
Max Act: 4.3206. Min Act: -0.1700
Data Index: 720797 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4456. Min Range: -4.4456
Max Act: 4.3206. Min Act: -0.1700
Data Index: 8524510 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4456. Min Range: -4.4456
Max Act: 4.2581. Min Act: -0.1700
Data Index: 6077942 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4456. Min Range: -4.4456
Max Act: 4.1644. Min Act: -0.1700
Data Index: 6366288 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4456. Min Range: -4.4456
Max Act: 4.1644. Min Act: -0.1700
Data Index: 5488232 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4456. Min Range: -4.4456
Max Act: 4.1644. Min Act: -0.1700
Data Index: 4165425 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4456. Min Range: -4.4456
Max Act: 4.1331. Min Act: -0.1700
Data Index: 4549406 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4456. Min Range: -4.4456
Max Act: 4.1331. Min Act: -0.1700
Data Index: 4506738 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4456. Min Range: -4.4456
Max Act: 4.1019. Min Act: -0.1700
Data Index: 755986 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4456. Min Range: -4.4456
Max Act: 4.1019. Min Act: -0.1700
Data Index: 6043652 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4456. Min Range: -4.4456
Max Act: 4.1019. Min Act: -0.1700
Data Index: 7910802 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4456. Min Range: -4.4456
Max Act: 4.1019. Min Act: -0.1700
Data Index: 2644711 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4456. Min Range: -4.4456
Max Act: 4.1019. Min Act: -0.1700
Data Index: 7672015 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4456. Min Range: -4.4456
Max Act: 4.0706. Min Act: -0.1700
Data Index: 4067773 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4456. Min Range: -4.4456
Max Act: 4.0706. Min Act: -0.1700
Data Index: 8779672 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4456. Min Range: -4.4456
Max Act: 4.0706. Min Act: -0.1700
Data Index: 1187115 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4456. Min Range: -4.4456
Max Act: 4.0081. Min Act: -0.1700
Data Index: 7437499 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4456. Min Range: -4.4456
Max Act: 4.0393. Min Act: -0.1700
Data Index: 2195692 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19