Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2721 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4210. Min Range: -8.4210
Max Act: 8.4210. Min Act: -0.1700
Data Index: 7452192 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4210. Min Range: -8.4210
Max Act: 8.3585. Min Act: -0.1700
Data Index: 2746309 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4210. Min Range: -8.4210
Max Act: 8.1085. Min Act: -0.1700
Data Index: 8627406 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4210. Min Range: -8.4210
Max Act: 8.1085. Min Act: -0.1700
Data Index: 6172695 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4210. Min Range: -8.4210
Max Act: 8.0460. Min Act: -0.1700
Data Index: 2797488 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4210. Min Range: -8.4210
Max Act: 8.0460. Min Act: -0.1700
Data Index: 7551579 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4210. Min Range: -8.4210
Max Act: 8.0460. Min Act: -0.1700
Data Index: 2740884 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4210. Min Range: -8.4210
Max Act: 7.9210. Min Act: -0.1700
Data Index: 7980801 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4210. Min Range: -8.4210
Max Act: 7.9210. Min Act: -0.1700
Data Index: 2697261 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4210. Min Range: -8.4210
Max Act: 7.9210. Min Act: -0.1700
Data Index: 5895738 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4210. Min Range: -8.4210
Max Act: 7.9210. Min Act: -0.1700
Data Index: 7044786 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4210. Min Range: -8.4210
Max Act: 7.9210. Min Act: -0.1700
Data Index: 1613216 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4210. Min Range: -8.4210
Max Act: 7.8585. Min Act: -0.1700
Data Index: 8510689 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4210. Min Range: -8.4210
Max Act: 7.8585. Min Act: -0.1700
Data Index: 3144406 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4210. Min Range: -8.4210
Max Act: 7.8585. Min Act: -0.1700
Data Index: 2807776 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4210. Min Range: -8.4210
Max Act: 7.8585. Min Act: -0.1700
Data Index: 5803368 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4210. Min Range: -8.4210
Max Act: 7.7960. Min Act: -0.1700
Data Index: 7227297 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4210. Min Range: -8.4210
Max Act: 7.7960. Min Act: -0.1700
Data Index: 2308337 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4210. Min Range: -8.4210
Max Act: 7.7960. Min Act: -0.1700
Data Index: 4203608 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4210. Min Range: -8.4210
Max Act: 7.7960. Min Act: -0.1700
Data Index: 7959690 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #19