Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3990 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9347. Min Range: -4.9347
Max Act: 4.9347. Min Act: -0.1700
Data Index: 4740875 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9347. Min Range: -4.9347
Max Act: 4.8410. Min Act: -0.1700
Data Index: 7958885 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9347. Min Range: -4.9347
Max Act: 4.8722. Min Act: -0.1700
Data Index: 5290060 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9347. Min Range: -4.9347
Max Act: 4.8410. Min Act: -0.1700
Data Index: 4054653 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9347. Min Range: -4.9347
Max Act: 4.8410. Min Act: -0.1700
Data Index: 5905913 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9347. Min Range: -4.9347
Max Act: 4.8097. Min Act: -0.1700
Data Index: 5905912 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9347. Min Range: -4.9347
Max Act: 4.8097. Min Act: -0.1700
Data Index: 111429 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9347. Min Range: -4.9347
Max Act: 4.8097. Min Act: -0.1700
Data Index: 3614585 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9347. Min Range: -4.9347
Max Act: 4.8097. Min Act: -0.1700
Data Index: 6668059 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9347. Min Range: -4.9347
Max Act: 4.8097. Min Act: -0.1700
Data Index: 1471098 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9347. Min Range: -4.9347
Max Act: 4.7785. Min Act: -0.1700
Data Index: 4861488 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9347. Min Range: -4.9347
Max Act: 4.7785. Min Act: -0.1700
Data Index: 1027227 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9347. Min Range: -4.9347
Max Act: 4.7472. Min Act: -0.1700
Data Index: 1964888 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9347. Min Range: -4.9347
Max Act: 4.7472. Min Act: -0.1700
Data Index: 4450987 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9347. Min Range: -4.9347
Max Act: 4.7472. Min Act: -0.1700
Data Index: 4751072 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9347. Min Range: -4.9347
Max Act: 4.7160. Min Act: -0.1700
Data Index: 2267731 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9347. Min Range: -4.9347
Max Act: 4.7160. Min Act: -0.1699
Data Index: 3623077 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9347. Min Range: -4.9347
Max Act: 4.7160. Min Act: -0.1700
Data Index: 2218691 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9347. Min Range: -4.9347
Max Act: 4.7160. Min Act: -0.1700
Data Index: 5160727 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9347. Min Range: -4.9347
Max Act: 4.7160. Min Act: -0.1700
Data Index: 1629513 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19