Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4122 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6675. Min Range: -6.6675
Max Act: 6.6675. Min Act: -0.1700
Data Index: 4433563 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6675. Min Range: -6.6675
Max Act: 6.5737. Min Act: -0.1700
Data Index: 3294219 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6675. Min Range: -6.6675
Max Act: 6.5425. Min Act: -0.1700
Data Index: 6336595 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6675. Min Range: -6.6675
Max Act: 6.3862. Min Act: -0.1700
Data Index: 7085832 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6675. Min Range: -6.6675
Max Act: 6.3550. Min Act: -0.1700
Data Index: 7818105 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6675. Min Range: -6.6675
Max Act: 6.3550. Min Act: -0.1700
Data Index: 7705958 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6675. Min Range: -6.6675
Max Act: 6.3550. Min Act: -0.1700
Data Index: 4086043 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6675. Min Range: -6.6675
Max Act: 6.3237. Min Act: -0.1700
Data Index: 8161898 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6675. Min Range: -6.6675
Max Act: 6.2612. Min Act: -0.1700
Data Index: 6471914 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6675. Min Range: -6.6675
Max Act: 6.3237. Min Act: -0.1700
Data Index: 5580881 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6675. Min Range: -6.6675
Max Act: 6.2612. Min Act: -0.1700
Data Index: 4558492 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6675. Min Range: -6.6675
Max Act: 6.2612. Min Act: -0.1700
Data Index: 4588341 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6675. Min Range: -6.6675
Max Act: 6.2612. Min Act: -0.1700
Data Index: 1171919 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6675. Min Range: -6.6675
Max Act: 6.2300. Min Act: -0.1700
Data Index: 8147152 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6675. Min Range: -6.6675
Max Act: 6.2300. Min Act: -0.1700
Data Index: 2691359 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6675. Min Range: -6.6675
Max Act: 6.1675. Min Act: -0.1700
Data Index: 352940 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6675. Min Range: -6.6675
Max Act: 6.1675. Min Act: -0.1700
Data Index: 5150346 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6675. Min Range: -6.6675
Max Act: 6.1675. Min Act: -0.1700
Data Index: 4235971 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6675. Min Range: -6.6675
Max Act: 6.1362. Min Act: -0.1700
Data Index: 6925809 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6675. Min Range: -6.6675
Max Act: 6.1362. Min Act: -0.1700
Data Index: 5086554 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19