Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2024 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8170. Min Range: -4.8170
Max Act: 4.8170. Min Act: -0.1700
Data Index: 6029242 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8170. Min Range: -4.8170
Max Act: 4.7544. Min Act: -0.1700
Data Index: 4993351 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8170. Min Range: -4.8170
Max Act: 4.7544. Min Act: -0.1700
Data Index: 7941064 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8170. Min Range: -4.8170
Max Act: 4.6919. Min Act: -0.1700
Data Index: 6382640 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8170. Min Range: -4.8170
Max Act: 4.6919. Min Act: -0.1700
Data Index: 8320537 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8170. Min Range: -4.8170
Max Act: 4.6919. Min Act: -0.1700
Data Index: 678948 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8170. Min Range: -4.8170
Max Act: 4.6919. Min Act: -0.1700
Data Index: 5370730 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8170. Min Range: -4.8170
Max Act: 4.6919. Min Act: -0.1700
Data Index: 7864254 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8170. Min Range: -4.8170
Max Act: 4.6607. Min Act: -0.1700
Data Index: 8402077 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8170. Min Range: -4.8170
Max Act: 4.6919. Min Act: -0.1700
Data Index: 6677293 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8170. Min Range: -4.8170
Max Act: 4.6607. Min Act: -0.1700
Data Index: 3044883 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8170. Min Range: -4.8170
Max Act: 4.6294. Min Act: -0.1700
Data Index: 1008244 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8170. Min Range: -4.8170
Max Act: 4.6294. Min Act: -0.1700
Data Index: 1123448 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8170. Min Range: -4.8170
Max Act: 4.6294. Min Act: -0.1700
Data Index: 4394919 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8170. Min Range: -4.8170
Max Act: 4.6294. Min Act: -0.1700
Data Index: 8345558 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8170. Min Range: -4.8170
Max Act: 4.5982. Min Act: -0.1700
Data Index: 4039415 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8170. Min Range: -4.8170
Max Act: 4.5669. Min Act: -0.1700
Data Index: 5432600 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8170. Min Range: -4.8170
Max Act: 4.5669. Min Act: -0.1700
Data Index: 8210021 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8170. Min Range: -4.8170
Max Act: 4.5982. Min Act: -0.1700
Data Index: 130974 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8170. Min Range: -4.8170
Max Act: 4.5669. Min Act: -0.1700
Data Index: 5490434 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #19