Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 512 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2565. Min Range: -5.2565
Max Act: 5.2565. Min Act: -0.1700
Data Index: 3881385 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2565. Min Range: -5.2565
Max Act: 5.1940. Min Act: -0.1700
Data Index: 6729331 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2565. Min Range: -5.2565
Max Act: 5.1627. Min Act: -0.1700
Data Index: 3807072 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2565. Min Range: -5.2565
Max Act: 5.1002. Min Act: -0.1700
Data Index: 8273969 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2565. Min Range: -5.2565
Max Act: 5.1627. Min Act: -0.1700
Data Index: 5118550 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2565. Min Range: -5.2565
Max Act: 5.1002. Min Act: -0.1700
Data Index: 3600514 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2565. Min Range: -5.2565
Max Act: 5.0690. Min Act: -0.1700
Data Index: 3897267 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2565. Min Range: -5.2565
Max Act: 5.0690. Min Act: -0.1700
Data Index: 6911230 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2565. Min Range: -5.2565
Max Act: 5.1002. Min Act: -0.1700
Data Index: 3674500 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2565. Min Range: -5.2565
Max Act: 5.0690. Min Act: -0.1700
Data Index: 2504072 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2565. Min Range: -5.2565
Max Act: 5.0690. Min Act: -0.1700
Data Index: 8084949 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2565. Min Range: -5.2565
Max Act: 5.0377. Min Act: -0.1700
Data Index: 782787 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2565. Min Range: -5.2565
Max Act: 4.9752. Min Act: -0.1700
Data Index: 8302457 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2565. Min Range: -5.2565
Max Act: 5.0065. Min Act: -0.1700
Data Index: 8529685 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2565. Min Range: -5.2565
Max Act: 5.0065. Min Act: -0.1700
Data Index: 8653764 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2565. Min Range: -5.2565
Max Act: 4.9752. Min Act: -0.1700
Data Index: 4855155 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2565. Min Range: -5.2565
Max Act: 4.9752. Min Act: -0.1700
Data Index: 373089 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2565. Min Range: -5.2565
Max Act: 5.0065. Min Act: -0.1700
Data Index: 4001044 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2565. Min Range: -5.2565
Max Act: 4.9752. Min Act: -0.1700
Data Index: 8280711 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2565. Min Range: -5.2565
Max Act: 5.0377. Min Act: -0.1700
Data Index: 305369 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19