Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1246 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9952. Min Range: -6.9952
Max Act: 6.9952. Min Act: -0.1700
Data Index: 6991013 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9952. Min Range: -6.9952
Max Act: 6.9952. Min Act: -0.1700
Data Index: 7052947 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9952. Min Range: -6.9952
Max Act: 6.9639. Min Act: -0.1700
Data Index: 5933943 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9952. Min Range: -6.9952
Max Act: 6.8077. Min Act: -0.1700
Data Index: 139677 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9952. Min Range: -6.9952
Max Act: 6.8389. Min Act: -0.1700
Data Index: 8292619 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9952. Min Range: -6.9952
Max Act: 6.7764. Min Act: -0.1700
Data Index: 3327602 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9952. Min Range: -6.9952
Max Act: 6.7764. Min Act: -0.1700
Data Index: 5291336 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9952. Min Range: -6.9952
Max Act: 6.7764. Min Act: -0.1700
Data Index: 385168 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9952. Min Range: -6.9952
Max Act: 6.8077. Min Act: -0.1700
Data Index: 3945692 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9952. Min Range: -6.9952
Max Act: 6.8077. Min Act: -0.1700
Data Index: 7144180 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9952. Min Range: -6.9952
Max Act: 6.7764. Min Act: -0.1700
Data Index: 3948766 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9952. Min Range: -6.9952
Max Act: 6.7764. Min Act: -0.1700
Data Index: 2029393 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9952. Min Range: -6.9952
Max Act: 6.7764. Min Act: -0.1700
Data Index: 3634730 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9952. Min Range: -6.9952
Max Act: 6.7452. Min Act: -0.1700
Data Index: 6258849 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9952. Min Range: -6.9952
Max Act: 6.7452. Min Act: -0.1700
Data Index: 3265372 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9952. Min Range: -6.9952
Max Act: 6.7139. Min Act: -0.1700
Data Index: 6324368 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9952. Min Range: -6.9952
Max Act: 6.7452. Min Act: -0.1700
Data Index: 2519962 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9952. Min Range: -6.9952
Max Act: 6.7139. Min Act: -0.1700
Data Index: 4437371 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9952. Min Range: -6.9952
Max Act: 6.7139. Min Act: -0.1700
Data Index: 4102829 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9952. Min Range: -6.9952
Max Act: 6.6514. Min Act: -0.1700
Data Index: 6135599 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #19