Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2839 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0094. Min Range: -7.0094
Max Act: 7.0094. Min Act: -0.1700
Data Index: 8541962 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0094. Min Range: -7.0094
Max Act: 7.0094. Min Act: -0.1700
Data Index: 1070565 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0094. Min Range: -7.0094
Max Act: 6.9781. Min Act: -0.1700
Data Index: 2305355 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0094. Min Range: -7.0094
Max Act: 6.9469. Min Act: -0.1700
Data Index: 525580 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0094. Min Range: -7.0094
Max Act: 6.9469. Min Act: -0.1700
Data Index: 1497745 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0094. Min Range: -7.0094
Max Act: 6.8531. Min Act: -0.1700
Data Index: 3669893 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0094. Min Range: -7.0094
Max Act: 6.8219. Min Act: -0.1700
Data Index: 25607 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0094. Min Range: -7.0094
Max Act: 6.7906. Min Act: -0.1700
Data Index: 4915690 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0094. Min Range: -7.0094
Max Act: 6.7906. Min Act: -0.1700
Data Index: 8522530 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0094. Min Range: -7.0094
Max Act: 6.7594. Min Act: -0.1700
Data Index: 2369223 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0094. Min Range: -7.0094
Max Act: 6.7594. Min Act: -0.1700
Data Index: 260832 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0094. Min Range: -7.0094
Max Act: 6.7594. Min Act: -0.1700
Data Index: 1300577 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0094. Min Range: -7.0094
Max Act: 6.7281. Min Act: -0.1700
Data Index: 3729572 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0094. Min Range: -7.0094
Max Act: 6.6969. Min Act: -0.1700
Data Index: 7999601 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0094. Min Range: -7.0094
Max Act: 6.6656. Min Act: -0.1700
Data Index: 7174770 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0094. Min Range: -7.0094
Max Act: 6.6656. Min Act: -0.1700
Data Index: 5197993 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0094. Min Range: -7.0094
Max Act: 6.6656. Min Act: -0.1700
Data Index: 692661 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0094. Min Range: -7.0094
Max Act: 6.6344. Min Act: -0.1700
Data Index: 6619993 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0094. Min Range: -7.0094
Max Act: 6.6656. Min Act: -0.1700
Data Index: 7973962 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0094. Min Range: -7.0094
Max Act: 6.6344. Min Act: -0.1700
Data Index: 2343484 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19