Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1963 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5533. Min Range: -5.5533
Max Act: 5.5533. Min Act: -0.1700
Data Index: 4063413 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5533. Min Range: -5.5533
Max Act: 5.4908. Min Act: -0.1700
Data Index: 8139838 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5533. Min Range: -5.5533
Max Act: 5.4283. Min Act: -0.1700
Data Index: 6622177 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5533. Min Range: -5.5533
Max Act: 5.4283. Min Act: -0.1700
Data Index: 8665182 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5533. Min Range: -5.5533
Max Act: 5.3971. Min Act: -0.1700
Data Index: 4239483 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5533. Min Range: -5.5533
Max Act: 5.3658. Min Act: -0.1700
Data Index: 1369119 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5533. Min Range: -5.5533
Max Act: 5.3658. Min Act: -0.1700
Data Index: 204918 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5533. Min Range: -5.5533
Max Act: 5.3346. Min Act: -0.1700
Data Index: 8617684 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5533. Min Range: -5.5533
Max Act: 5.3033. Min Act: -0.1700
Data Index: 1062596 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5533. Min Range: -5.5533
Max Act: 5.3033. Min Act: -0.1700
Data Index: 4944445 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5533. Min Range: -5.5533
Max Act: 5.3033. Min Act: -0.1700
Data Index: 1432028 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5533. Min Range: -5.5533
Max Act: 5.2721. Min Act: -0.1700
Data Index: 7596648 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5533. Min Range: -5.5533
Max Act: 5.2721. Min Act: -0.1700
Data Index: 8112786 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5533. Min Range: -5.5533
Max Act: 5.2721. Min Act: -0.1700
Data Index: 307954 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5533. Min Range: -5.5533
Max Act: 5.2408. Min Act: -0.1700
Data Index: 2788828 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5533. Min Range: -5.5533
Max Act: 5.1471. Min Act: -0.1700
Data Index: 4165893 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5533. Min Range: -5.5533
Max Act: 5.1783. Min Act: -0.1700
Data Index: 3178134 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5533. Min Range: -5.5533
Max Act: 5.1783. Min Act: -0.1700
Data Index: 1432032 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5533. Min Range: -5.5533
Max Act: 5.1471. Min Act: -0.1700
Data Index: 4588865 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5533. Min Range: -5.5533
Max Act: 5.1471. Min Act: -0.1700
Data Index: 4210148 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #19