Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4763 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3695. Min Range: -7.3695
Max Act: 7.3695. Min Act: -0.1700
Data Index: 5016881 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3695. Min Range: -7.3695
Max Act: 7.3383. Min Act: -0.1700
Data Index: 3657600 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3695. Min Range: -7.3695
Max Act: 7.2758. Min Act: -0.1700
Data Index: 8241095 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3695. Min Range: -7.3695
Max Act: 7.2445. Min Act: -0.1700
Data Index: 7011583 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3695. Min Range: -7.3695
Max Act: 7.2445. Min Act: -0.1700
Data Index: 2908361 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3695. Min Range: -7.3695
Max Act: 7.1508. Min Act: -0.1700
Data Index: 7036635 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3695. Min Range: -7.3695
Max Act: 7.1820. Min Act: -0.1700
Data Index: 2607843 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3695. Min Range: -7.3695
Max Act: 7.1508. Min Act: -0.1700
Data Index: 5179481 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3695. Min Range: -7.3695
Max Act: 7.0883. Min Act: -0.1700
Data Index: 5542527 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3695. Min Range: -7.3695
Max Act: 7.0883. Min Act: -0.1700
Data Index: 6357727 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3695. Min Range: -7.3695
Max Act: 6.9945. Min Act: -0.1700
Data Index: 5529360 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3695. Min Range: -7.3695
Max Act: 6.9320. Min Act: -0.1700
Data Index: 3234666 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3695. Min Range: -7.3695
Max Act: 6.9008. Min Act: -0.1700
Data Index: 1061179 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3695. Min Range: -7.3695
Max Act: 6.9320. Min Act: -0.1700
Data Index: 1784711 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3695. Min Range: -7.3695
Max Act: 6.8383. Min Act: -0.1700
Data Index: 954242 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3695. Min Range: -7.3695
Max Act: 6.8383. Min Act: -0.1700
Data Index: 2266645 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3695. Min Range: -7.3695
Max Act: 6.8383. Min Act: -0.1700
Data Index: 1352445 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3695. Min Range: -7.3695
Max Act: 6.7758. Min Act: -0.1700
Data Index: 1738370 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3695. Min Range: -7.3695
Max Act: 6.7758. Min Act: -0.1700
Data Index: 7863811 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3695. Min Range: -7.3695
Max Act: 6.7758. Min Act: -0.1700
Data Index: 2908360 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19