Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2561 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9519. Min Range: -4.9519
Max Act: 4.9519. Min Act: -0.1700
Data Index: 3816485 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9519. Min Range: -4.9519
Max Act: 4.9206. Min Act: -0.1700
Data Index: 4535273 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9519. Min Range: -4.9519
Max Act: 4.9206. Min Act: -0.1700
Data Index: 7653128 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9519. Min Range: -4.9519
Max Act: 4.8894. Min Act: -0.1700
Data Index: 7205148 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9519. Min Range: -4.9519
Max Act: 4.8581. Min Act: -0.1700
Data Index: 5046670 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9519. Min Range: -4.9519
Max Act: 4.8269. Min Act: -0.1700
Data Index: 8190348 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9519. Min Range: -4.9519
Max Act: 4.8269. Min Act: -0.1700
Data Index: 276968 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9519. Min Range: -4.9519
Max Act: 4.8269. Min Act: -0.1700
Data Index: 2187197 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9519. Min Range: -4.9519
Max Act: 4.7956. Min Act: -0.1700
Data Index: 3240709 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9519. Min Range: -4.9519
Max Act: 4.7644. Min Act: -0.1700
Data Index: 7672585 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9519. Min Range: -4.9519
Max Act: 4.7644. Min Act: -0.1700
Data Index: 622991 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9519. Min Range: -4.9519
Max Act: 4.7644. Min Act: -0.1700
Data Index: 7656444 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9519. Min Range: -4.9519
Max Act: 4.7644. Min Act: -0.1700
Data Index: 8467709 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9519. Min Range: -4.9519
Max Act: 4.7644. Min Act: -0.1700
Data Index: 2060661 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9519. Min Range: -4.9519
Max Act: 4.7644. Min Act: -0.1700
Data Index: 7205145 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9519. Min Range: -4.9519
Max Act: 4.7331. Min Act: -0.1700
Data Index: 392580 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9519. Min Range: -4.9519
Max Act: 4.7331. Min Act: -0.1700
Data Index: 3075461 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9519. Min Range: -4.9519
Max Act: 4.7019. Min Act: -0.1700
Data Index: 1641650 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9519. Min Range: -4.9519
Max Act: 4.7331. Min Act: -0.1700
Data Index: 2031263 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9519. Min Range: -4.9519
Max Act: 4.7331. Min Act: -0.1700
Data Index: 4922262 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #19