Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2427 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 15.8715. Min Range: -15.8715
Max Act: 15.8715. Min Act: -0.1700
Data Index: 344052 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 15.8715. Min Range: -15.8715
Max Act: 15.3715. Min Act: -0.1700
Data Index: 3659709 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 15.8715. Min Range: -15.8715
Max Act: 15.2465. Min Act: -0.1700
Data Index: 2206672 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 15.8715. Min Range: -15.8715
Max Act: 15.3090. Min Act: -0.1700
Data Index: 7025949 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 15.8715. Min Range: -15.8715
Max Act: 15.2465. Min Act: -0.1700
Data Index: 5941843 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 15.8715. Min Range: -15.8715
Max Act: 15.1840. Min Act: -0.1700
Data Index: 854771 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 15.8715. Min Range: -15.8715
Max Act: 15.0590. Min Act: -0.1700
Data Index: 3182594 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 15.8715. Min Range: -15.8715
Max Act: 15.1215. Min Act: -0.1700
Data Index: 2888511 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 15.8715. Min Range: -15.8715
Max Act: 15.1215. Min Act: -0.1700
Data Index: 1220996 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 15.8715. Min Range: -15.8715
Max Act: 15.0590. Min Act: -0.1700
Data Index: 426470 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 15.8715. Min Range: -15.8715
Max Act: 15.0590. Min Act: -0.1700
Data Index: 7031741 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 15.8715. Min Range: -15.8715
Max Act: 14.9340. Min Act: -0.1700
Data Index: 4298453 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 15.8715. Min Range: -15.8715
Max Act: 14.8715. Min Act: -0.1700
Data Index: 507197 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 15.8715. Min Range: -15.8715
Max Act: 14.8715. Min Act: -0.1700
Data Index: 279078 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 15.8715. Min Range: -15.8715
Max Act: 14.8715. Min Act: -0.1700
Data Index: 1493881 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 15.8715. Min Range: -15.8715
Max Act: 14.8090. Min Act: -0.1700
Data Index: 4491238 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 15.8715. Min Range: -15.8715
Max Act: 14.8715. Min Act: -0.1700
Data Index: 4288441 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 15.8715. Min Range: -15.8715
Max Act: 14.7465. Min Act: -0.1700
Data Index: 2509949 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 15.8715. Min Range: -15.8715
Max Act: 14.8715. Min Act: -0.1700
Data Index: 3476755 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 15.8715. Min Range: -15.8715
Max Act: 14.8090. Min Act: -0.1700
Data Index: 2275394 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19