Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 550 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.0403. Min Range: -12.0403
Max Act: 12.0403. Min Act: -0.1700
Data Index: 7006548 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.0403. Min Range: -12.0403
Max Act: 11.6653. Min Act: -0.1700
Data Index: 138845 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.0403. Min Range: -12.0403
Max Act: 11.6653. Min Act: -0.1700
Data Index: 4135203 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.0403. Min Range: -12.0403
Max Act: 11.6028. Min Act: -0.1700
Data Index: 3302682 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.0403. Min Range: -12.0403
Max Act: 11.4153. Min Act: -0.1700
Data Index: 229153 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.0403. Min Range: -12.0403
Max Act: 11.2903. Min Act: -0.1700
Data Index: 7045178 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.0403. Min Range: -12.0403
Max Act: 11.2903. Min Act: -0.1700
Data Index: 4362735 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.0403. Min Range: -12.0403
Max Act: 11.1653. Min Act: -0.1700
Data Index: 1404809 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.0403. Min Range: -12.0403
Max Act: 11.1653. Min Act: -0.1700
Data Index: 681591 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.0403. Min Range: -12.0403
Max Act: 11.1653. Min Act: -0.1700
Data Index: 1234898 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.0403. Min Range: -12.0403
Max Act: 11.1028. Min Act: -0.1700
Data Index: 5512831 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.0403. Min Range: -12.0403
Max Act: 11.1028. Min Act: -0.1700
Data Index: 6806149 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.0403. Min Range: -12.0403
Max Act: 11.0403. Min Act: -0.1700
Data Index: 3790570 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.0403. Min Range: -12.0403
Max Act: 11.0403. Min Act: -0.1700
Data Index: 7240576 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.0403. Min Range: -12.0403
Max Act: 11.0403. Min Act: -0.1700
Data Index: 8390269 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.0403. Min Range: -12.0403
Max Act: 11.0403. Min Act: -0.1700
Data Index: 1435723 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.0403. Min Range: -12.0403
Max Act: 11.0403. Min Act: -0.1700
Data Index: 8285308 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.0403. Min Range: -12.0403
Max Act: 11.0403. Min Act: -0.1700
Data Index: 2958863 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.0403. Min Range: -12.0403
Max Act: 10.9153. Min Act: -0.1700
Data Index: 5128549 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.0403. Min Range: -12.0403
Max Act: 10.9778. Min Act: -0.1700
Data Index: 8605515 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #19