Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 515 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3771. Min Range: -3.3771
Max Act: 3.3771. Min Act: -0.1700
Data Index: 8383826 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3771. Min Range: -3.3771
Max Act: 3.3457. Min Act: -0.1700
Data Index: 6916143 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3771. Min Range: -3.3771
Max Act: 3.3143. Min Act: -0.1700
Data Index: 5845212 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3771. Min Range: -3.3771
Max Act: 3.2986. Min Act: -0.1700
Data Index: 3649091 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3771. Min Range: -3.3771
Max Act: 3.2829. Min Act: -0.1700
Data Index: 2847602 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3771. Min Range: -3.3771
Max Act: 3.2043. Min Act: -0.1700
Data Index: 391730 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3771. Min Range: -3.3771
Max Act: 3.2201. Min Act: -0.1700
Data Index: 8809771 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3771. Min Range: -3.3771
Max Act: 3.2043. Min Act: -0.1700
Data Index: 739429 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3771. Min Range: -3.3771
Max Act: 3.2201. Min Act: -0.1700
Data Index: 6567851 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3771. Min Range: -3.3771
Max Act: 3.2043. Min Act: -0.1700
Data Index: 47473 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3771. Min Range: -3.3771
Max Act: 3.1886. Min Act: -0.1700
Data Index: 7751711 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3771. Min Range: -3.3771
Max Act: 3.1729. Min Act: -0.1700
Data Index: 8509233 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3771. Min Range: -3.3771
Max Act: 3.1414. Min Act: -0.1700
Data Index: 8402239 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3771. Min Range: -3.3771
Max Act: 3.1571. Min Act: -0.1700
Data Index: 1538721 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3771. Min Range: -3.3771
Max Act: 3.1571. Min Act: -0.1700
Data Index: 5031554 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3771. Min Range: -3.3771
Max Act: 3.1571. Min Act: -0.1700
Data Index: 8026407 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3771. Min Range: -3.3771
Max Act: 3.1414. Min Act: -0.1700
Data Index: 3025715 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3771. Min Range: -3.3771
Max Act: 3.1414. Min Act: -0.1700
Data Index: 651087 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3771. Min Range: -3.3771
Max Act: 3.1257. Min Act: -0.1700
Data Index: 8485675 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3771. Min Range: -3.3771
Max Act: 3.1414. Min Act: -0.1700
Data Index: 4739524 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #19