Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2477 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.5992. Min Act: -0.1700
Data Index: 201749 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.5367. Min Act: -0.1700
Data Index: 800579 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.5367. Min Act: -0.1700
Data Index: 8748450 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.4430. Min Act: -0.1700
Data Index: 3803917 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.4430. Min Act: -0.1700
Data Index: 2964143 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.3492. Min Act: -0.1700
Data Index: 2672990 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.3492. Min Act: -0.1700
Data Index: 2667517 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.3805. Min Act: -0.1700
Data Index: 1737161 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.3180. Min Act: -0.1700
Data Index: 8814545 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.2554. Min Act: -0.1700
Data Index: 6546251 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.2867. Min Act: -0.1700
Data Index: 5546993 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.2554. Min Act: -0.1700
Data Index: 6736390 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.2554. Min Act: -0.1700
Data Index: 2766266 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.1929. Min Act: -0.1700
Data Index: 2168660 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.2242. Min Act: -0.1700
Data Index: 459341 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.2242. Min Act: -0.1700
Data Index: 7699687 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.2242. Min Act: -0.1700
Data Index: 6610318 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.1929. Min Act: -0.1700
Data Index: 3532185 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.1929. Min Act: -0.1700
Data Index: 744125 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.1929. Min Act: -0.1700
Data Index: 2009027 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #19