Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5348 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1391. Min Range: -6.1391
Max Act: 6.1391. Min Act: -0.1700
Data Index: 321873 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1391. Min Range: -6.1391
Max Act: 6.1391. Min Act: -0.1700
Data Index: 2232999 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1391. Min Range: -6.1391
Max Act: 6.0766. Min Act: -0.1700
Data Index: 321872 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1391. Min Range: -6.1391
Max Act: 6.0141. Min Act: -0.1700
Data Index: 3617260 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1391. Min Range: -6.1391
Max Act: 5.9828. Min Act: -0.1700
Data Index: 249973 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1391. Min Range: -6.1391
Max Act: 5.9828. Min Act: -0.1700
Data Index: 321874 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1391. Min Range: -6.1391
Max Act: 5.9516. Min Act: -0.1700
Data Index: 8308686 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1391. Min Range: -6.1391
Max Act: 5.9516. Min Act: -0.1700
Data Index: 4265033 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1391. Min Range: -6.1391
Max Act: 5.9203. Min Act: -0.1700
Data Index: 2232998 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1391. Min Range: -6.1391
Max Act: 5.9516. Min Act: -0.1700
Data Index: 4053695 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1391. Min Range: -6.1391
Max Act: 5.8891. Min Act: -0.1700
Data Index: 8040824 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1391. Min Range: -6.1391
Max Act: 5.8891. Min Act: -0.1700
Data Index: 2612091 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1391. Min Range: -6.1391
Max Act: 5.8578. Min Act: -0.1700
Data Index: 8308685 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1391. Min Range: -6.1391
Max Act: 5.8266. Min Act: -0.1700
Data Index: 3617269 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1391. Min Range: -6.1391
Max Act: 5.8578. Min Act: -0.1700
Data Index: 3418593 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1391. Min Range: -6.1391
Max Act: 5.7953. Min Act: -0.1700
Data Index: 1910999 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1391. Min Range: -6.1391
Max Act: 5.7953. Min Act: -0.1700
Data Index: 476341 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1391. Min Range: -6.1391
Max Act: 5.7641. Min Act: -0.1700
Data Index: 3522607 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1391. Min Range: -6.1391
Max Act: 5.7953. Min Act: -0.1700
Data Index: 4693277 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1391. Min Range: -6.1391
Max Act: 5.7641. Min Act: -0.1700
Data Index: 3371366 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #19