Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2727 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7760. Min Range: -5.7760
Max Act: 5.7760. Min Act: -0.1700
Data Index: 5453004 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7760. Min Range: -5.7760
Max Act: 5.4323. Min Act: -0.1700
Data Index: 1763999 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7760. Min Range: -5.7760
Max Act: 5.4323. Min Act: -0.1700
Data Index: 7088966 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7760. Min Range: -5.7760
Max Act: 5.2760. Min Act: -0.1700
Data Index: 2650507 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7760. Min Range: -5.7760
Max Act: 5.1823. Min Act: -0.1700
Data Index: 6585793 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7760. Min Range: -5.7760
Max Act: 5.1510. Min Act: -0.1700
Data Index: 7546330 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7760. Min Range: -5.7760
Max Act: 5.1198. Min Act: -0.1700
Data Index: 385624 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7760. Min Range: -5.7760
Max Act: 5.1198. Min Act: -0.1700
Data Index: 3470667 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7760. Min Range: -5.7760
Max Act: 5.1198. Min Act: -0.1700
Data Index: 1169296 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7760. Min Range: -5.7760
Max Act: 5.0885. Min Act: -0.1700
Data Index: 1544239 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7760. Min Range: -5.7760
Max Act: 5.0885. Min Act: -0.1700
Data Index: 3879676 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7760. Min Range: -5.7760
Max Act: 5.0573. Min Act: -0.1700
Data Index: 2875991 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7760. Min Range: -5.7760
Max Act: 5.0573. Min Act: -0.1700
Data Index: 2069875 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7760. Min Range: -5.7760
Max Act: 5.0260. Min Act: -0.1700
Data Index: 8763340 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7760. Min Range: -5.7760
Max Act: 5.0260. Min Act: -0.1700
Data Index: 6776295 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7760. Min Range: -5.7760
Max Act: 5.0260. Min Act: -0.1700
Data Index: 2334405 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7760. Min Range: -5.7760
Max Act: 5.0260. Min Act: -0.1700
Data Index: 2644713 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7760. Min Range: -5.7760
Max Act: 4.9948. Min Act: -0.1700
Data Index: 2758870 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7760. Min Range: -5.7760
Max Act: 4.9948. Min Act: -0.1700
Data Index: 6452199 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7760. Min Range: -5.7760
Max Act: 4.9635. Min Act: -0.1700
Data Index: 2712419 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #19