Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3546 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9901. Min Range: -8.9901
Max Act: 8.9901. Min Act: -0.1700
Data Index: 7153001 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9901. Min Range: -8.9901
Max Act: 8.9276. Min Act: -0.1700
Data Index: 5606270 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9901. Min Range: -8.9901
Max Act: 8.8651. Min Act: -0.1700
Data Index: 757705 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9901. Min Range: -8.9901
Max Act: 8.8026. Min Act: -0.1700
Data Index: 8259608 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9901. Min Range: -8.9901
Max Act: 8.8026. Min Act: -0.1700
Data Index: 7773187 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9901. Min Range: -8.9901
Max Act: 8.8026. Min Act: -0.1700
Data Index: 6501375 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9901. Min Range: -8.9901
Max Act: 8.6776. Min Act: -0.1700
Data Index: 398821 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9901. Min Range: -8.9901
Max Act: 8.6151. Min Act: -0.1700
Data Index: 3559552 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9901. Min Range: -8.9901
Max Act: 8.5526. Min Act: -0.1700
Data Index: 8741199 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9901. Min Range: -8.9901
Max Act: 8.5526. Min Act: -0.1700
Data Index: 4432950 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9901. Min Range: -8.9901
Max Act: 8.4276. Min Act: -0.1700
Data Index: 1074590 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9901. Min Range: -8.9901
Max Act: 8.4276. Min Act: -0.1700
Data Index: 7497926 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9901. Min Range: -8.9901
Max Act: 8.4276. Min Act: -0.1700
Data Index: 969911 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9901. Min Range: -8.9901
Max Act: 8.4276. Min Act: -0.1700
Data Index: 3338365 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9901. Min Range: -8.9901
Max Act: 8.4276. Min Act: -0.1700
Data Index: 4163107 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9901. Min Range: -8.9901
Max Act: 8.4276. Min Act: -0.1700
Data Index: 8134626 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9901. Min Range: -8.9901
Max Act: 8.4276. Min Act: -0.1700
Data Index: 3245373 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9901. Min Range: -8.9901
Max Act: 8.3651. Min Act: -0.1700
Data Index: 1949113 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9901. Min Range: -8.9901
Max Act: 8.3651. Min Act: -0.1700
Data Index: 4660561 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9901. Min Range: -8.9901
Max Act: 8.3651. Min Act: -0.1700
Data Index: 7959211 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #19