Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 168 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1438. Min Range: -9.1438
Max Act: 9.1438. Min Act: -0.1700
Data Index: 8189732 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1438. Min Range: -9.1438
Max Act: 9.1438. Min Act: -0.1700
Data Index: 72239 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1438. Min Range: -9.1438
Max Act: 9.0188. Min Act: -0.1700
Data Index: 1411447 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1438. Min Range: -9.1438
Max Act: 9.0188. Min Act: -0.1700
Data Index: 833936 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1438. Min Range: -9.1438
Max Act: 8.8938. Min Act: -0.1700
Data Index: 1056736 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1438. Min Range: -9.1438
Max Act: 8.9563. Min Act: -0.1700
Data Index: 5084719 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1438. Min Range: -9.1438
Max Act: 8.8313. Min Act: -0.1700
Data Index: 8602797 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1438. Min Range: -9.1438
Max Act: 8.8313. Min Act: -0.1700
Data Index: 8686893 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1438. Min Range: -9.1438
Max Act: 8.7688. Min Act: -0.1700
Data Index: 340939 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1438. Min Range: -9.1438
Max Act: 8.7688. Min Act: -0.1700
Data Index: 7435332 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1438. Min Range: -9.1438
Max Act: 8.7688. Min Act: -0.1700
Data Index: 4771421 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1438. Min Range: -9.1438
Max Act: 8.7688. Min Act: -0.1700
Data Index: 8552901 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1438. Min Range: -9.1438
Max Act: 8.7063. Min Act: -0.1700
Data Index: 4236710 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1438. Min Range: -9.1438
Max Act: 8.7063. Min Act: -0.1700
Data Index: 5048145 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1438. Min Range: -9.1438
Max Act: 8.6438. Min Act: -0.1700
Data Index: 7403738 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1438. Min Range: -9.1438
Max Act: 8.5813. Min Act: -0.1700
Data Index: 4649184 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1438. Min Range: -9.1438
Max Act: 8.5813. Min Act: -0.1700
Data Index: 4075021 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1438. Min Range: -9.1438
Max Act: 8.5813. Min Act: -0.1700
Data Index: 801349 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1438. Min Range: -9.1438
Max Act: 8.5813. Min Act: -0.1700
Data Index: 1864828 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1438. Min Range: -9.1438
Max Act: 8.6438. Min Act: -0.1700
Data Index: 3889722 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #19