Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3771 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8954. Min Range: -4.8954
Max Act: 4.8954. Min Act: -0.1700
Data Index: 2261902 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8954. Min Range: -4.8954
Max Act: 4.7704. Min Act: -0.1700
Data Index: 7170314 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8954. Min Range: -4.8954
Max Act: 4.7392. Min Act: -0.1700
Data Index: 5529196 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8954. Min Range: -4.8954
Max Act: 4.7392. Min Act: -0.1700
Data Index: 4921385 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8954. Min Range: -4.8954
Max Act: 4.7079. Min Act: -0.1700
Data Index: 2826973 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8954. Min Range: -4.8954
Max Act: 4.6767. Min Act: -0.1700
Data Index: 8819238 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8954. Min Range: -4.8954
Max Act: 4.6454. Min Act: -0.1700
Data Index: 4768455 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8954. Min Range: -4.8954
Max Act: 4.5829. Min Act: -0.1700
Data Index: 7697980 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8954. Min Range: -4.8954
Max Act: 4.5517. Min Act: -0.1700
Data Index: 5767134 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8954. Min Range: -4.8954
Max Act: 4.5204. Min Act: -0.1700
Data Index: 4997401 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8954. Min Range: -4.8954
Max Act: 4.5204. Min Act: -0.1700
Data Index: 6801543 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8954. Min Range: -4.8954
Max Act: 4.4892. Min Act: -0.1700
Data Index: 364103 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8954. Min Range: -4.8954
Max Act: 4.5204. Min Act: -0.1700
Data Index: 2142729 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8954. Min Range: -4.8954
Max Act: 4.4892. Min Act: -0.1700
Data Index: 3913873 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8954. Min Range: -4.8954
Max Act: 4.4892. Min Act: -0.1700
Data Index: 765532 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8954. Min Range: -4.8954
Max Act: 4.4892. Min Act: -0.1700
Data Index: 6675798 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8954. Min Range: -4.8954
Max Act: 4.4579. Min Act: -0.1700
Data Index: 8477108 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8954. Min Range: -4.8954
Max Act: 4.4579. Min Act: -0.1700
Data Index: 815738 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8954. Min Range: -4.8954
Max Act: 4.4267. Min Act: -0.1700
Data Index: 6512507 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8954. Min Range: -4.8954
Max Act: 4.4892. Min Act: -0.1700
Data Index: 4898064 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #19