Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3521 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2342. Min Range: -4.2342
Max Act: 4.2342. Min Act: -0.1700
Data Index: 7035661 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2342. Min Range: -4.2342
Max Act: 4.1717. Min Act: -0.1700
Data Index: 7458881 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2342. Min Range: -4.2342
Max Act: 4.1405. Min Act: -0.1700
Data Index: 4010998 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2342. Min Range: -4.2342
Max Act: 4.1092. Min Act: -0.1700
Data Index: 6533097 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2342. Min Range: -4.2342
Max Act: 4.0780. Min Act: -0.1700
Data Index: 4010996 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2342. Min Range: -4.2342
Max Act: 4.0467. Min Act: -0.1700
Data Index: 3034961 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2342. Min Range: -4.2342
Max Act: 3.9842. Min Act: -0.1700
Data Index: 3134095 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2342. Min Range: -4.2342
Max Act: 3.9842. Min Act: -0.1700
Data Index: 1737221 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2342. Min Range: -4.2342
Max Act: 3.9529. Min Act: -0.1700
Data Index: 1777424 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2342. Min Range: -4.2342
Max Act: 3.9529. Min Act: -0.1700
Data Index: 2302380 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2342. Min Range: -4.2342
Max Act: 3.9217. Min Act: -0.1700
Data Index: 6136086 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2342. Min Range: -4.2342
Max Act: 3.9217. Min Act: -0.1700
Data Index: 5958589 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2342. Min Range: -4.2342
Max Act: 3.8904. Min Act: -0.1700
Data Index: 2302388 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2342. Min Range: -4.2342
Max Act: 3.8748. Min Act: -0.1700
Data Index: 6212218 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2342. Min Range: -4.2342
Max Act: 3.8591. Min Act: -0.1700
Data Index: 7293024 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2342. Min Range: -4.2342
Max Act: 3.8748. Min Act: -0.1700
Data Index: 6676711 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2342. Min Range: -4.2342
Max Act: 3.8748. Min Act: -0.1700
Data Index: 7866170 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2342. Min Range: -4.2342
Max Act: 3.8591. Min Act: -0.1700
Data Index: 3004960 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2342. Min Range: -4.2342
Max Act: 3.8591. Min Act: -0.1700
Data Index: 6829779 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2342. Min Range: -4.2342
Max Act: 3.8122. Min Act: -0.1700
Data Index: 671085 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19