Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2474 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.8465. Min Range: -7.8465
Max Act: 7.8465. Min Act: -0.1700
Data Index: 2952683 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8465. Min Range: -7.8465
Max Act: 7.7215. Min Act: -0.1700
Data Index: 3307676 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8465. Min Range: -7.8465
Max Act: 7.6590. Min Act: -0.1700
Data Index: 495827 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8465. Min Range: -7.8465
Max Act: 7.5028. Min Act: -0.1700
Data Index: 2323952 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8465. Min Range: -7.8465
Max Act: 7.5028. Min Act: -0.1700
Data Index: 293566 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8465. Min Range: -7.8465
Max Act: 7.4715. Min Act: -0.1700
Data Index: 2918893 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8465. Min Range: -7.8465
Max Act: 7.4715. Min Act: -0.1700
Data Index: 158325 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8465. Min Range: -7.8465
Max Act: 7.4715. Min Act: -0.1700
Data Index: 2533933 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8465. Min Range: -7.8465
Max Act: 7.4715. Min Act: -0.1700
Data Index: 6534680 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8465. Min Range: -7.8465
Max Act: 7.3778. Min Act: -0.1700
Data Index: 187451 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8465. Min Range: -7.8465
Max Act: 7.4090. Min Act: -0.1700
Data Index: 5944011 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8465. Min Range: -7.8465
Max Act: 7.3778. Min Act: -0.1700
Data Index: 8523866 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8465. Min Range: -7.8465
Max Act: 7.3778. Min Act: -0.1700
Data Index: 373352 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8465. Min Range: -7.8465
Max Act: 7.4090. Min Act: -0.1700
Data Index: 1655501 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8465. Min Range: -7.8465
Max Act: 7.3465. Min Act: -0.1700
Data Index: 5348353 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8465. Min Range: -7.8465
Max Act: 7.3778. Min Act: -0.1700
Data Index: 4036225 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8465. Min Range: -7.8465
Max Act: 7.2840. Min Act: -0.1700
Data Index: 7208393 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8465. Min Range: -7.8465
Max Act: 7.2528. Min Act: -0.1700
Data Index: 4407304 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8465. Min Range: -7.8465
Max Act: 7.2215. Min Act: -0.1700
Data Index: 689966 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8465. Min Range: -7.8465
Max Act: 7.2215. Min Act: -0.1700
Data Index: 6397290 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #19