Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3037 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3316. Min Range: -8.3316
Max Act: 8.3316. Min Act: -0.1700
Data Index: 2355246 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3316. Min Range: -8.3316
Max Act: 8.0191. Min Act: -0.1700
Data Index: 5067815 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3316. Min Range: -8.3316
Max Act: 7.8941. Min Act: -0.1700
Data Index: 896781 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3316. Min Range: -8.3316
Max Act: 7.8629. Min Act: -0.1700
Data Index: 4506432 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3316. Min Range: -8.3316
Max Act: 7.8629. Min Act: -0.1700
Data Index: 5170897 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3316. Min Range: -8.3316
Max Act: 7.8316. Min Act: -0.1700
Data Index: 5347122 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3316. Min Range: -8.3316
Max Act: 7.8004. Min Act: -0.1700
Data Index: 3836356 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3316. Min Range: -8.3316
Max Act: 7.8004. Min Act: -0.1700
Data Index: 592009 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3316. Min Range: -8.3316
Max Act: 7.8004. Min Act: -0.1700
Data Index: 8149634 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3316. Min Range: -8.3316
Max Act: 7.7691. Min Act: -0.1700
Data Index: 8149633 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3316. Min Range: -8.3316
Max Act: 7.7379. Min Act: -0.1700
Data Index: 5868077 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3316. Min Range: -8.3316
Max Act: 7.7066. Min Act: -0.1700
Data Index: 1347560 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3316. Min Range: -8.3316
Max Act: 7.6441. Min Act: -0.1700
Data Index: 1992576 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3316. Min Range: -8.3316
Max Act: 7.6441. Min Act: -0.1700
Data Index: 5850679 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3316. Min Range: -8.3316
Max Act: 7.6754. Min Act: -0.1700
Data Index: 2455249 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3316. Min Range: -8.3316
Max Act: 7.6441. Min Act: -0.1700
Data Index: 3425424 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3316. Min Range: -8.3316
Max Act: 7.6129. Min Act: -0.1700
Data Index: 8696060 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3316. Min Range: -8.3316
Max Act: 7.6441. Min Act: -0.1700
Data Index: 4083350 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3316. Min Range: -8.3316
Max Act: 7.6129. Min Act: -0.1700
Data Index: 3224122 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3316. Min Range: -8.3316
Max Act: 7.6129. Min Act: -0.1700
Data Index: 1128168 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #19