Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4330 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6006. Min Range: -3.6006
Max Act: 3.5693. Min Act: -0.1700
Data Index: 6444551 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6006. Min Range: -3.6006
Max Act: 3.6006. Min Act: -0.1700
Data Index: 702065 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6006. Min Range: -3.6006
Max Act: 3.5693. Min Act: -0.1700
Data Index: 800325 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6006. Min Range: -3.6006
Max Act: 3.5693. Min Act: -0.1700
Data Index: 596933 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6006. Min Range: -3.6006
Max Act: 3.5380. Min Act: -0.1700
Data Index: 4044906 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6006. Min Range: -3.6006
Max Act: 3.5380. Min Act: -0.1700
Data Index: 596932 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6006. Min Range: -3.6006
Max Act: 3.5067. Min Act: -0.1700
Data Index: 2459366 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6006. Min Range: -3.6006
Max Act: 3.5067. Min Act: -0.1700
Data Index: 4863746 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6006. Min Range: -3.6006
Max Act: 3.5067. Min Act: -0.1700
Data Index: 4626503 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6006. Min Range: -3.6006
Max Act: 3.5067. Min Act: -0.1700
Data Index: 7782108 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6006. Min Range: -3.6006
Max Act: 3.4754. Min Act: -0.1700
Data Index: 5512980 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6006. Min Range: -3.6006
Max Act: 3.5067. Min Act: -0.1700
Data Index: 6608434 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6006. Min Range: -3.6006
Max Act: 3.4754. Min Act: -0.1700
Data Index: 8165455 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6006. Min Range: -3.6006
Max Act: 3.4754. Min Act: -0.1700
Data Index: 4977936 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6006. Min Range: -3.6006
Max Act: 3.4754. Min Act: -0.1700
Data Index: 4482148 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6006. Min Range: -3.6006
Max Act: 3.4754. Min Act: -0.1700
Data Index: 7847318 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6006. Min Range: -3.6006
Max Act: 3.4440. Min Act: -0.1700
Data Index: 7495676 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6006. Min Range: -3.6006
Max Act: 3.4440. Min Act: -0.1700
Data Index: 4061505 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6006. Min Range: -3.6006
Max Act: 3.4440. Min Act: -0.1700
Data Index: 2553549 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6006. Min Range: -3.6006
Max Act: 3.4127. Min Act: -0.1700
Data Index: 7495675 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #19