Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3480 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4828. Min Range: -8.4828
Max Act: 8.4828. Min Act: -0.1700
Data Index: 135560 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4828. Min Range: -8.4828
Max Act: 8.4828. Min Act: -0.1700
Data Index: 5144721 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4828. Min Range: -8.4828
Max Act: 8.4828. Min Act: -0.1700
Data Index: 4874207 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4828. Min Range: -8.4828
Max Act: 8.4203. Min Act: -0.1700
Data Index: 2890491 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4828. Min Range: -8.4828
Max Act: 8.4203. Min Act: -0.1700
Data Index: 1898539 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4828. Min Range: -8.4828
Max Act: 8.4203. Min Act: -0.1700
Data Index: 4724556 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4828. Min Range: -8.4828
Max Act: 8.3578. Min Act: -0.1700
Data Index: 510994 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4828. Min Range: -8.4828
Max Act: 8.3578. Min Act: -0.1700
Data Index: 243206 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4828. Min Range: -8.4828
Max Act: 8.2953. Min Act: -0.1700
Data Index: 5767173 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4828. Min Range: -8.4828
Max Act: 8.2953. Min Act: -0.1700
Data Index: 2101833 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4828. Min Range: -8.4828
Max Act: 8.2328. Min Act: -0.1700
Data Index: 3427897 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4828. Min Range: -8.4828
Max Act: 8.2328. Min Act: -0.1700
Data Index: 1615859 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4828. Min Range: -8.4828
Max Act: 8.2328. Min Act: -0.1700
Data Index: 6564113 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4828. Min Range: -8.4828
Max Act: 8.1703. Min Act: -0.1700
Data Index: 5985469 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4828. Min Range: -8.4828
Max Act: 8.1703. Min Act: -0.1700
Data Index: 6544648 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4828. Min Range: -8.4828
Max Act: 8.1703. Min Act: -0.1700
Data Index: 6447584 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4828. Min Range: -8.4828
Max Act: 8.1703. Min Act: -0.1700
Data Index: 6096260 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4828. Min Range: -8.4828
Max Act: 8.1703. Min Act: -0.1700
Data Index: 2706732 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4828. Min Range: -8.4828
Max Act: 8.1078. Min Act: -0.1700
Data Index: 2479653 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4828. Min Range: -8.4828
Max Act: 8.1078. Min Act: -0.1700
Data Index: 3637433 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19