Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2480 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8448. Min Range: -3.8448
Max Act: 3.8448. Min Act: -0.1700
Data Index: 5137278 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8448. Min Range: -3.8448
Max Act: 3.8448. Min Act: -0.1700
Data Index: 5792223 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8448. Min Range: -3.8448
Max Act: 3.7823. Min Act: -0.1700
Data Index: 5222999 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8448. Min Range: -3.8448
Max Act: 3.8136. Min Act: -0.1700
Data Index: 8175443 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8448. Min Range: -3.8448
Max Act: 3.7510. Min Act: -0.1700
Data Index: 5055553 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8448. Min Range: -3.8448
Max Act: 3.7197. Min Act: -0.1700
Data Index: 2055737 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8448. Min Range: -3.8448
Max Act: 3.7510. Min Act: -0.1700
Data Index: 256219 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8448. Min Range: -3.8448
Max Act: 3.7510. Min Act: -0.1700
Data Index: 512878 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8448. Min Range: -3.8448
Max Act: 3.7197. Min Act: -0.1700
Data Index: 6695392 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8448. Min Range: -3.8448
Max Act: 3.7510. Min Act: -0.1700
Data Index: 2788288 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8448. Min Range: -3.8448
Max Act: 3.7510. Min Act: -0.1700
Data Index: 2427810 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8448. Min Range: -3.8448
Max Act: 3.7197. Min Act: -0.1700
Data Index: 3185325 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8448. Min Range: -3.8448
Max Act: 3.7197. Min Act: -0.1700
Data Index: 3527119 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8448. Min Range: -3.8448
Max Act: 3.7197. Min Act: -0.1700
Data Index: 3645887 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8448. Min Range: -3.8448
Max Act: 3.7197. Min Act: -0.1700
Data Index: 3738314 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8448. Min Range: -3.8448
Max Act: 3.7197. Min Act: -0.1700
Data Index: 2265223 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8448. Min Range: -3.8448
Max Act: 3.7197. Min Act: -0.1700
Data Index: 1412596 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8448. Min Range: -3.8448
Max Act: 3.7197. Min Act: -0.1700
Data Index: 418729 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8448. Min Range: -3.8448
Max Act: 3.7197. Min Act: -0.1700
Data Index: 4172434 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8448. Min Range: -3.8448
Max Act: 3.7197. Min Act: -0.1700
Data Index: 4456813 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19