Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3218 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2201. Min Range: -5.2201
Max Act: 5.2201. Min Act: -0.1700
Data Index: 1696466 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2201. Min Range: -5.2201
Max Act: 5.1264. Min Act: -0.1700
Data Index: 2216449 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2201. Min Range: -5.2201
Max Act: 5.1264. Min Act: -0.1700
Data Index: 2501540 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2201. Min Range: -5.2201
Max Act: 5.0951. Min Act: -0.1700
Data Index: 8198287 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2201. Min Range: -5.2201
Max Act: 5.0639. Min Act: -0.1700
Data Index: 1123838 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2201. Min Range: -5.2201
Max Act: 5.0639. Min Act: -0.1700
Data Index: 8792995 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2201. Min Range: -5.2201
Max Act: 5.0639. Min Act: -0.1700
Data Index: 8773866 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2201. Min Range: -5.2201
Max Act: 5.0326. Min Act: -0.1700
Data Index: 7698056 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2201. Min Range: -5.2201
Max Act: 5.0326. Min Act: -0.1700
Data Index: 3053185 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2201. Min Range: -5.2201
Max Act: 5.0326. Min Act: -0.1700
Data Index: 2400549 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2201. Min Range: -5.2201
Max Act: 5.0014. Min Act: -0.1700
Data Index: 7703170 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2201. Min Range: -5.2201
Max Act: 4.9389. Min Act: -0.1700
Data Index: 665863 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2201. Min Range: -5.2201
Max Act: 4.9389. Min Act: -0.1700
Data Index: 1539982 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2201. Min Range: -5.2201
Max Act: 4.9389. Min Act: -0.1700
Data Index: 3373349 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2201. Min Range: -5.2201
Max Act: 4.9076. Min Act: -0.1700
Data Index: 2124499 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2201. Min Range: -5.2201
Max Act: 4.9389. Min Act: -0.1700
Data Index: 4734355 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2201. Min Range: -5.2201
Max Act: 4.9076. Min Act: -0.1700
Data Index: 436518 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2201. Min Range: -5.2201
Max Act: 4.9076. Min Act: -0.1700
Data Index: 4003096 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2201. Min Range: -5.2201
Max Act: 4.9389. Min Act: -0.1700
Data Index: 4094329 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2201. Min Range: -5.2201
Max Act: 4.9076. Min Act: -0.1700
Data Index: 5672885 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #19