Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5838 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5112. Min Range: -6.5112
Max Act: 6.5112. Min Act: -0.1700
Data Index: 4855051 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5112. Min Range: -6.5112
Max Act: 6.2300. Min Act: -0.1700
Data Index: 337009 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5112. Min Range: -6.5112
Max Act: 6.1362. Min Act: -0.1700
Data Index: 7400106 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5112. Min Range: -6.5112
Max Act: 6.1050. Min Act: -0.1700
Data Index: 8552249 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5112. Min Range: -6.5112
Max Act: 6.0737. Min Act: -0.1700
Data Index: 6044993 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5112. Min Range: -6.5112
Max Act: 6.0425. Min Act: -0.1700
Data Index: 951292 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5112. Min Range: -6.5112
Max Act: 6.0112. Min Act: -0.1700
Data Index: 3860740 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5112. Min Range: -6.5112
Max Act: 5.9800. Min Act: -0.1700
Data Index: 1182907 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5112. Min Range: -6.5112
Max Act: 6.0112. Min Act: -0.1700
Data Index: 2719055 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5112. Min Range: -6.5112
Max Act: 5.9800. Min Act: -0.1700
Data Index: 3917905 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5112. Min Range: -6.5112
Max Act: 5.9487. Min Act: -0.1700
Data Index: 4586387 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5112. Min Range: -6.5112
Max Act: 5.9487. Min Act: -0.1700
Data Index: 7223555 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5112. Min Range: -6.5112
Max Act: 5.8862. Min Act: -0.1700
Data Index: 5310419 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5112. Min Range: -6.5112
Max Act: 5.8862. Min Act: -0.1700
Data Index: 7426700 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5112. Min Range: -6.5112
Max Act: 5.8862. Min Act: -0.1700
Data Index: 2503581 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5112. Min Range: -6.5112
Max Act: 5.8550. Min Act: -0.1700
Data Index: 5095803 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5112. Min Range: -6.5112
Max Act: 5.8237. Min Act: -0.1700
Data Index: 2465008 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5112. Min Range: -6.5112
Max Act: 5.7925. Min Act: -0.1700
Data Index: 7124869 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5112. Min Range: -6.5112
Max Act: 5.8237. Min Act: -0.1700
Data Index: 2688648 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5112. Min Range: -6.5112
Max Act: 5.8237. Min Act: -0.1700
Data Index: 8338773 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #19