Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4123 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7150. Min Range: -6.7150
Max Act: 6.7150. Min Act: -0.1700
Data Index: 36259 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7150. Min Range: -6.7150
Max Act: 6.6212. Min Act: -0.1700
Data Index: 4972537 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7150. Min Range: -6.7150
Max Act: 6.4650. Min Act: -0.1700
Data Index: 4972538 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7150. Min Range: -6.7150
Max Act: 6.3400. Min Act: -0.1700
Data Index: 3056074 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7150. Min Range: -6.7150
Max Act: 6.3087. Min Act: -0.1700
Data Index: 781017 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7150. Min Range: -6.7150
Max Act: 6.2462. Min Act: -0.1700
Data Index: 1394091 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7150. Min Range: -6.7150
Max Act: 6.2150. Min Act: -0.1700
Data Index: 7192966 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7150. Min Range: -6.7150
Max Act: 6.2150. Min Act: -0.1700
Data Index: 478757 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7150. Min Range: -6.7150
Max Act: 6.1837. Min Act: -0.1700
Data Index: 4103855 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7150. Min Range: -6.7150
Max Act: 6.1525. Min Act: -0.1700
Data Index: 1990383 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7150. Min Range: -6.7150
Max Act: 6.1837. Min Act: -0.1700
Data Index: 1719908 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7150. Min Range: -6.7150
Max Act: 6.1525. Min Act: -0.1700
Data Index: 3963286 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7150. Min Range: -6.7150
Max Act: 6.1525. Min Act: -0.1700
Data Index: 2776478 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7150. Min Range: -6.7150
Max Act: 6.1212. Min Act: -0.1700
Data Index: 8485784 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7150. Min Range: -6.7150
Max Act: 6.1212. Min Act: -0.1700
Data Index: 558583 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7150. Min Range: -6.7150
Max Act: 6.1212. Min Act: -0.1700
Data Index: 7507994 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7150. Min Range: -6.7150
Max Act: 6.1212. Min Act: -0.1700
Data Index: 2725140 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7150. Min Range: -6.7150
Max Act: 6.0900. Min Act: -0.1700
Data Index: 1429006 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7150. Min Range: -6.7150
Max Act: 6.0587. Min Act: -0.1700
Data Index: 8485798 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7150. Min Range: -6.7150
Max Act: 6.0587. Min Act: -0.1700
Data Index: 1993337 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19