Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1688 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1446. Min Range: -5.1446
Max Act: 5.1446. Min Act: -0.1700
Data Index: 6573521 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1446. Min Range: -5.1446
Max Act: 4.8946. Min Act: -0.1700
Data Index: 7142092 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1446. Min Range: -5.1446
Max Act: 4.8633. Min Act: -0.1700
Data Index: 7156262 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1446. Min Range: -5.1446
Max Act: 4.8008. Min Act: -0.1700
Data Index: 8558060 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1446. Min Range: -5.1446
Max Act: 4.8008. Min Act: -0.1700
Data Index: 5729216 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1446. Min Range: -5.1446
Max Act: 4.8008. Min Act: -0.1700
Data Index: 2762491 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1446. Min Range: -5.1446
Max Act: 4.7696. Min Act: -0.1700
Data Index: 4214957 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1446. Min Range: -5.1446
Max Act: 4.7696. Min Act: -0.1700
Data Index: 6969654 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1446. Min Range: -5.1446
Max Act: 4.7383. Min Act: -0.1700
Data Index: 4293270 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1446. Min Range: -5.1446
Max Act: 4.6758. Min Act: -0.1700
Data Index: 6220516 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1446. Min Range: -5.1446
Max Act: 4.6758. Min Act: -0.1700
Data Index: 5817760 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1446. Min Range: -5.1446
Max Act: 4.6133. Min Act: -0.1700
Data Index: 2795814 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1446. Min Range: -5.1446
Max Act: 4.6758. Min Act: -0.1700
Data Index: 5230251 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1446. Min Range: -5.1446
Max Act: 4.6446. Min Act: -0.1700
Data Index: 4950822 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1446. Min Range: -5.1446
Max Act: 4.6133. Min Act: -0.1700
Data Index: 1463890 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1446. Min Range: -5.1446
Max Act: 4.6133. Min Act: -0.1700
Data Index: 895134 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1446. Min Range: -5.1446
Max Act: 4.6133. Min Act: -0.1700
Data Index: 3783792 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1446. Min Range: -5.1446
Max Act: 4.5821. Min Act: -0.1700
Data Index: 7539991 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1446. Min Range: -5.1446
Max Act: 4.5821. Min Act: -0.1700
Data Index: 6530612 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1446. Min Range: -5.1446
Max Act: 4.5508. Min Act: -0.1700
Data Index: 1770899 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #19