Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5515 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5932. Min Range: -5.5932
Max Act: 5.5932. Min Act: -0.1700
Data Index: 1246104 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5932. Min Range: -5.5932
Max Act: 5.5307. Min Act: -0.1700
Data Index: 86640 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5932. Min Range: -5.5932
Max Act: 5.4369. Min Act: -0.1700
Data Index: 6051781 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5932. Min Range: -5.5932
Max Act: 5.4369. Min Act: -0.1700
Data Index: 6903242 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5932. Min Range: -5.5932
Max Act: 5.3744. Min Act: -0.1700
Data Index: 6687677 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5932. Min Range: -5.5932
Max Act: 5.3744. Min Act: -0.1700
Data Index: 5322750 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5932. Min Range: -5.5932
Max Act: 5.3744. Min Act: -0.1700
Data Index: 2157422 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5932. Min Range: -5.5932
Max Act: 5.3432. Min Act: -0.1700
Data Index: 5453851 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5932. Min Range: -5.5932
Max Act: 5.3432. Min Act: -0.1700
Data Index: 8369108 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5932. Min Range: -5.5932
Max Act: 5.3744. Min Act: -0.1700
Data Index: 6282366 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5932. Min Range: -5.5932
Max Act: 5.3432. Min Act: -0.1700
Data Index: 1610845 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5932. Min Range: -5.5932
Max Act: 5.3119. Min Act: -0.1700
Data Index: 1219802 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5932. Min Range: -5.5932
Max Act: 5.3119. Min Act: -0.1700
Data Index: 5078423 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5932. Min Range: -5.5932
Max Act: 5.3119. Min Act: -0.1700
Data Index: 8580237 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5932. Min Range: -5.5932
Max Act: 5.3119. Min Act: -0.1700
Data Index: 5885455 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5932. Min Range: -5.5932
Max Act: 5.2807. Min Act: -0.1700
Data Index: 2337850 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5932. Min Range: -5.5932
Max Act: 5.2807. Min Act: -0.1700
Data Index: 5584012 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5932. Min Range: -5.5932
Max Act: 5.2807. Min Act: -0.1700
Data Index: 5924123 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5932. Min Range: -5.5932
Max Act: 5.2807. Min Act: -0.1700
Data Index: 2050780 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5932. Min Range: -5.5932
Max Act: 5.2807. Min Act: -0.1700
Data Index: 1213111 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #19