Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4337 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4675. Min Range: -8.4675
Max Act: 8.4675. Min Act: -0.1700
Data Index: 2855061 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4675. Min Range: -8.4675
Max Act: 8.4050. Min Act: -0.1700
Data Index: 7453869 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4675. Min Range: -8.4675
Max Act: 8.3425. Min Act: -0.1700
Data Index: 5694997 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4675. Min Range: -8.4675
Max Act: 8.2800. Min Act: -0.1700
Data Index: 4131961 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4675. Min Range: -8.4675
Max Act: 8.2175. Min Act: -0.1700
Data Index: 1436866 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4675. Min Range: -8.4675
Max Act: 8.1550. Min Act: -0.1700
Data Index: 6613974 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4675. Min Range: -8.4675
Max Act: 8.0925. Min Act: -0.1700
Data Index: 8797381 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4675. Min Range: -8.4675
Max Act: 8.0300. Min Act: -0.1700
Data Index: 3371300 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4675. Min Range: -8.4675
Max Act: 8.0300. Min Act: -0.1700
Data Index: 2855060 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4675. Min Range: -8.4675
Max Act: 8.0300. Min Act: -0.1700
Data Index: 6939477 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4675. Min Range: -8.4675
Max Act: 7.9675. Min Act: -0.1700
Data Index: 5688076 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4675. Min Range: -8.4675
Max Act: 7.9362. Min Act: -0.1700
Data Index: 6906900 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4675. Min Range: -8.4675
Max Act: 7.9362. Min Act: -0.1700
Data Index: 4861373 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4675. Min Range: -8.4675
Max Act: 7.9050. Min Act: -0.1700
Data Index: 2534487 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4675. Min Range: -8.4675
Max Act: 7.9050. Min Act: -0.1700
Data Index: 1240728 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4675. Min Range: -8.4675
Max Act: 7.8737. Min Act: -0.1700
Data Index: 7509018 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4675. Min Range: -8.4675
Max Act: 7.8425. Min Act: -0.1700
Data Index: 4814535 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4675. Min Range: -8.4675
Max Act: 7.8425. Min Act: -0.1700
Data Index: 6707773 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4675. Min Range: -8.4675
Max Act: 7.8425. Min Act: -0.1700
Data Index: 2259795 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4675. Min Range: -8.4675
Max Act: 7.8425. Min Act: -0.1700
Data Index: 3355811 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #19