Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3541 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0530. Min Range: -5.0530
Max Act: 5.0530. Min Act: -0.1700
Data Index: 489694 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0530. Min Range: -5.0530
Max Act: 4.9905. Min Act: -0.1700
Data Index: 4605336 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0530. Min Range: -5.0530
Max Act: 4.9593. Min Act: -0.1700
Data Index: 4919381 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0530. Min Range: -5.0530
Max Act: 4.9593. Min Act: -0.1700
Data Index: 4341039 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0530. Min Range: -5.0530
Max Act: 4.8968. Min Act: -0.1700
Data Index: 8227900 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0530. Min Range: -5.0530
Max Act: 4.8655. Min Act: -0.1700
Data Index: 5027138 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0530. Min Range: -5.0530
Max Act: 4.8655. Min Act: -0.1700
Data Index: 2519813 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0530. Min Range: -5.0530
Max Act: 4.8655. Min Act: -0.1700
Data Index: 7973623 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0530. Min Range: -5.0530
Max Act: 4.8030. Min Act: -0.1700
Data Index: 8547191 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0530. Min Range: -5.0530
Max Act: 4.8655. Min Act: -0.1700
Data Index: 4170455 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0530. Min Range: -5.0530
Max Act: 4.8343. Min Act: -0.1700
Data Index: 4518849 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0530. Min Range: -5.0530
Max Act: 4.8655. Min Act: -0.1700
Data Index: 5047287 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0530. Min Range: -5.0530
Max Act: 4.8968. Min Act: -0.1700
Data Index: 5530585 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0530. Min Range: -5.0530
Max Act: 4.8030. Min Act: -0.1700
Data Index: 3877697 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0530. Min Range: -5.0530
Max Act: 4.8655. Min Act: -0.1700
Data Index: 5990294 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0530. Min Range: -5.0530
Max Act: 4.8343. Min Act: -0.1700
Data Index: 2518850 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0530. Min Range: -5.0530
Max Act: 4.8343. Min Act: -0.1700
Data Index: 2630322 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0530. Min Range: -5.0530
Max Act: 4.8030. Min Act: -0.1700
Data Index: 804348 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0530. Min Range: -5.0530
Max Act: 4.8343. Min Act: -0.1700
Data Index: 5170842 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0530. Min Range: -5.0530
Max Act: 4.8343. Min Act: -0.1700
Data Index: 5271560 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #19