Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 740 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 15.6223. Min Range: -15.6223
Max Act: 15.6223. Min Act: -0.1700
Data Index: 8496893 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 15.6223. Min Range: -15.6223
Max Act: 15.3723. Min Act: -0.1700
Data Index: 2211048 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 15.6223. Min Range: -15.6223
Max Act: 15.3723. Min Act: -0.1700
Data Index: 1010473 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 15.6223. Min Range: -15.6223
Max Act: 15.1848. Min Act: -0.1699
Data Index: 5574518 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 15.6223. Min Range: -15.6223
Max Act: 15.1848. Min Act: -0.1700
Data Index: 5013877 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 15.6223. Min Range: -15.6223
Max Act: 15.1848. Min Act: -0.1700
Data Index: 4788997 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 15.6223. Min Range: -15.6223
Max Act: 15.1848. Min Act: -0.1700
Data Index: 4389432 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 15.6223. Min Range: -15.6223
Max Act: 15.0598. Min Act: -0.1700
Data Index: 4243576 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 15.6223. Min Range: -15.6223
Max Act: 14.9973. Min Act: -0.1700
Data Index: 3336923 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 15.6223. Min Range: -15.6223
Max Act: 14.8723. Min Act: -0.1700
Data Index: 1323251 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 15.6223. Min Range: -15.6223
Max Act: 14.8723. Min Act: -0.1700
Data Index: 7957903 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 15.6223. Min Range: -15.6223
Max Act: 14.8723. Min Act: -0.1700
Data Index: 1046748 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 15.6223. Min Range: -15.6223
Max Act: 14.7473. Min Act: -0.1700
Data Index: 1826777 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 15.6223. Min Range: -15.6223
Max Act: 14.6848. Min Act: -0.1700
Data Index: 5816975 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 15.6223. Min Range: -15.6223
Max Act: 14.6848. Min Act: -0.1700
Data Index: 581397 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 15.6223. Min Range: -15.6223
Max Act: 14.6848. Min Act: -0.1700
Data Index: 869380 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 15.6223. Min Range: -15.6223
Max Act: 14.6223. Min Act: -0.1700
Data Index: 3983389 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 15.6223. Min Range: -15.6223
Max Act: 14.6223. Min Act: -0.1699
Data Index: 7739069 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 15.6223. Min Range: -15.6223
Max Act: 14.6223. Min Act: -0.1700
Data Index: 6990455 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 15.6223. Min Range: -15.6223
Max Act: 14.5598. Min Act: -0.1700
Data Index: 1535483 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #19