Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1369 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5929. Min Range: -3.5929
Max Act: 3.5929. Min Act: -0.1700
Data Index: 7630614 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5929. Min Range: -3.5929
Max Act: 3.4833. Min Act: -0.1700
Data Index: 6616200 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5929. Min Range: -3.5929
Max Act: 3.3579. Min Act: -0.1700
Data Index: 7520049 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5929. Min Range: -3.5929
Max Act: 3.3736. Min Act: -0.1700
Data Index: 8280148 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5929. Min Range: -3.5929
Max Act: 3.3579. Min Act: -0.1700
Data Index: 4567952 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5929. Min Range: -3.5929
Max Act: 3.3579. Min Act: -0.1700
Data Index: 4265968 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5929. Min Range: -3.5929
Max Act: 3.3265. Min Act: -0.1700
Data Index: 4930096 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5929. Min Range: -3.5929
Max Act: 3.2951. Min Act: -0.1700
Data Index: 4773254 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5929. Min Range: -3.5929
Max Act: 3.2951. Min Act: -0.1700
Data Index: 2260834 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5929. Min Range: -3.5929
Max Act: 3.2794. Min Act: -0.1700
Data Index: 561002 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5929. Min Range: -3.5929
Max Act: 3.2951. Min Act: -0.1700
Data Index: 957543 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5929. Min Range: -3.5929
Max Act: 3.2637. Min Act: -0.1700
Data Index: 799222 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5929. Min Range: -3.5929
Max Act: 3.2637. Min Act: -0.1700
Data Index: 6127909 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5929. Min Range: -3.5929
Max Act: 3.2794. Min Act: -0.1700
Data Index: 3855729 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5929. Min Range: -3.5929
Max Act: 3.2637. Min Act: -0.1700
Data Index: 8467460 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5929. Min Range: -3.5929
Max Act: 3.2323. Min Act: -0.1700
Data Index: 2452369 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5929. Min Range: -3.5929
Max Act: 3.2480. Min Act: -0.1700
Data Index: 1484735 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5929. Min Range: -3.5929
Max Act: 3.2323. Min Act: -0.1700
Data Index: 2412390 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5929. Min Range: -3.5929
Max Act: 3.2323. Min Act: -0.1700
Data Index: 6821031 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5929. Min Range: -3.5929
Max Act: 3.2165. Min Act: -0.1700
Data Index: 5909103 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #19