Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3578 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3419. Min Range: -8.3419
Max Act: 8.3419. Min Act: -0.1700
Data Index: 490264 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3419. Min Range: -8.3419
Max Act: 8.2169. Min Act: -0.1700
Data Index: 4574121 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3419. Min Range: -8.3419
Max Act: 8.0919. Min Act: -0.1700
Data Index: 3158095 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3419. Min Range: -8.3419
Max Act: 8.0919. Min Act: -0.1699
Data Index: 5004260 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3419. Min Range: -8.3419
Max Act: 7.9669. Min Act: -0.1700
Data Index: 1595565 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3419. Min Range: -8.3419
Max Act: 7.9669. Min Act: -0.1700
Data Index: 6344367 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3419. Min Range: -8.3419
Max Act: 7.9669. Min Act: -0.1700
Data Index: 8764700 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3419. Min Range: -8.3419
Max Act: 7.9044. Min Act: -0.1700
Data Index: 1831345 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3419. Min Range: -8.3419
Max Act: 7.8419. Min Act: -0.1700
Data Index: 1230809 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3419. Min Range: -8.3419
Max Act: 7.8419. Min Act: -0.1700
Data Index: 504844 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3419. Min Range: -8.3419
Max Act: 7.8419. Min Act: -0.1700
Data Index: 5456485 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3419. Min Range: -8.3419
Max Act: 7.7794. Min Act: -0.1700
Data Index: 3200450 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3419. Min Range: -8.3419
Max Act: 7.7794. Min Act: -0.1700
Data Index: 992247 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3419. Min Range: -8.3419
Max Act: 7.9669. Min Act: -0.1700
Data Index: 3216356 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3419. Min Range: -8.3419
Max Act: 7.6544. Min Act: -0.1700
Data Index: 1377719 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3419. Min Range: -8.3419
Max Act: 7.7169. Min Act: -0.1700
Data Index: 5953359 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3419. Min Range: -8.3419
Max Act: 7.7169. Min Act: -0.1700
Data Index: 4498167 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3419. Min Range: -8.3419
Max Act: 7.7169. Min Act: -0.1700
Data Index: 8108975 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3419. Min Range: -8.3419
Max Act: 7.7794. Min Act: -0.1700
Data Index: 2123609 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3419. Min Range: -8.3419
Max Act: 7.7169. Min Act: -0.1700
Data Index: 5419385 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #19