Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3905 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8963. Min Range: -4.8963
Max Act: 4.8963. Min Act: -0.1700
Data Index: 5998291 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8963. Min Range: -4.8963
Max Act: 4.5526. Min Act: -0.1700
Data Index: 5296171 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8963. Min Range: -4.8963
Max Act: 4.4901. Min Act: -0.1700
Data Index: 4000183 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8963. Min Range: -4.8963
Max Act: 4.4588. Min Act: -0.1700
Data Index: 2986518 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8963. Min Range: -4.8963
Max Act: 4.4276. Min Act: -0.1700
Data Index: 3957886 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8963. Min Range: -4.8963
Max Act: 4.3963. Min Act: -0.1700
Data Index: 4418205 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8963. Min Range: -4.8963
Max Act: 4.3963. Min Act: -0.1700
Data Index: 1692797 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8963. Min Range: -4.8963
Max Act: 4.3963. Min Act: -0.1700
Data Index: 1028009 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8963. Min Range: -4.8963
Max Act: 4.3651. Min Act: -0.1700
Data Index: 2148621 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8963. Min Range: -4.8963
Max Act: 4.3338. Min Act: -0.1700
Data Index: 1902149 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8963. Min Range: -4.8963
Max Act: 4.3651. Min Act: -0.1700
Data Index: 4441603 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8963. Min Range: -4.8963
Max Act: 4.3338. Min Act: -0.1700
Data Index: 777618 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8963. Min Range: -4.8963
Max Act: 4.3338. Min Act: -0.1700
Data Index: 6659629 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8963. Min Range: -4.8963
Max Act: 4.3026. Min Act: -0.1700
Data Index: 7729365 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8963. Min Range: -4.8963
Max Act: 4.3026. Min Act: -0.1700
Data Index: 935035 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8963. Min Range: -4.8963
Max Act: 4.3026. Min Act: -0.1700
Data Index: 852251 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8963. Min Range: -4.8963
Max Act: 4.3026. Min Act: -0.1700
Data Index: 4231655 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8963. Min Range: -4.8963
Max Act: 4.2713. Min Act: -0.1700
Data Index: 1534688 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8963. Min Range: -4.8963
Max Act: 4.2401. Min Act: -0.1700
Data Index: 6593583 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8963. Min Range: -4.8963
Max Act: 4.2401. Min Act: -0.1700
Data Index: 4006566 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #19