Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3694 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0292. Min Range: -8.0292
Max Act: 8.0292. Min Act: -0.1700
Data Index: 5339313 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0292. Min Range: -8.0292
Max Act: 7.8729. Min Act: -0.1700
Data Index: 7389025 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0292. Min Range: -8.0292
Max Act: 7.8104. Min Act: -0.1700
Data Index: 8228362 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0292. Min Range: -8.0292
Max Act: 7.8417. Min Act: -0.1700
Data Index: 4921008 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0292. Min Range: -8.0292
Max Act: 7.8104. Min Act: -0.1700
Data Index: 4587658 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0292. Min Range: -8.0292
Max Act: 7.8417. Min Act: -0.1700
Data Index: 7505042 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0292. Min Range: -8.0292
Max Act: 7.7167. Min Act: -0.1700
Data Index: 5454116 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0292. Min Range: -8.0292
Max Act: 7.6854. Min Act: -0.1700
Data Index: 64367 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0292. Min Range: -8.0292
Max Act: 7.6854. Min Act: -0.1700
Data Index: 3254715 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0292. Min Range: -8.0292
Max Act: 7.6854. Min Act: -0.1700
Data Index: 7480494 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0292. Min Range: -8.0292
Max Act: 7.6229. Min Act: -0.1700
Data Index: 3215112 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0292. Min Range: -8.0292
Max Act: 7.6229. Min Act: -0.1700
Data Index: 1267635 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0292. Min Range: -8.0292
Max Act: 7.5917. Min Act: -0.1700
Data Index: 6836469 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0292. Min Range: -8.0292
Max Act: 7.5917. Min Act: -0.1700
Data Index: 2344151 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0292. Min Range: -8.0292
Max Act: 7.5917. Min Act: -0.1700
Data Index: 454982 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0292. Min Range: -8.0292
Max Act: 7.5604. Min Act: -0.1700
Data Index: 3244371 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0292. Min Range: -8.0292
Max Act: 7.5917. Min Act: -0.1700
Data Index: 2527338 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0292. Min Range: -8.0292
Max Act: 7.6229. Min Act: -0.1700
Data Index: 960319 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0292. Min Range: -8.0292
Max Act: 7.5604. Min Act: -0.1700
Data Index: 8700395 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0292. Min Range: -8.0292
Max Act: 7.5604. Min Act: -0.1700
Data Index: 4435061 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #19