Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4087 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8034. Min Range: -1.8034
Max Act: 1.8034. Min Act: -0.1700
Data Index: 2588582 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8034. Min Range: -1.8034
Max Act: 1.7603. Min Act: -0.1700
Data Index: 3371318 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8034. Min Range: -1.8034
Max Act: 1.7775. Min Act: -0.1700
Data Index: 5488729 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8034. Min Range: -1.8034
Max Act: 1.7775. Min Act: -0.1700
Data Index: 1483647 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8034. Min Range: -1.8034
Max Act: 1.7603. Min Act: -0.1700
Data Index: 4501731 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8034. Min Range: -1.8034
Max Act: 1.7516. Min Act: -0.1700
Data Index: 6373927 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8034. Min Range: -1.8034
Max Act: 1.7603. Min Act: -0.1700
Data Index: 4960595 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8034. Min Range: -1.8034
Max Act: 1.7689. Min Act: -0.1699
Data Index: 1012634 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8034. Min Range: -1.8034
Max Act: 1.7603. Min Act: -0.1700
Data Index: 5019795 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8034. Min Range: -1.8034
Max Act: 1.7430. Min Act: -0.1700
Data Index: 942283 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8034. Min Range: -1.8034
Max Act: 1.7430. Min Act: -0.1700
Data Index: 6321085 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8034. Min Range: -1.8034
Max Act: 1.7344. Min Act: -0.1700
Data Index: 1383009 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8034. Min Range: -1.8034
Max Act: 1.7516. Min Act: -0.1700
Data Index: 7523512 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8034. Min Range: -1.8034
Max Act: 1.7516. Min Act: -0.1700
Data Index: 3697833 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8034. Min Range: -1.8034
Max Act: 1.7516. Min Act: -0.1700
Data Index: 6455023 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8034. Min Range: -1.8034
Max Act: 1.7344. Min Act: -0.1700
Data Index: 2040443 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8034. Min Range: -1.8034
Max Act: 1.7344. Min Act: -0.1700
Data Index: 3650021 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8034. Min Range: -1.8034
Max Act: 1.7257. Min Act: -0.1700
Data Index: 3313659 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8034. Min Range: -1.8034
Max Act: 1.7344. Min Act: -0.1700
Data Index: 293225 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8034. Min Range: -1.8034
Max Act: 1.7257. Min Act: -0.1700
Data Index: 1486999 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19