Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3481 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6158. Min Range: -4.6158
Max Act: 4.6158. Min Act: -0.1699
Data Index: 3044839 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6158. Min Range: -4.6158
Max Act: 4.5221. Min Act: -0.1700
Data Index: 3110256 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6158. Min Range: -4.6158
Max Act: 4.5221. Min Act: -0.1700
Data Index: 1470811 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6158. Min Range: -4.6158
Max Act: 4.5221. Min Act: -0.1700
Data Index: 1419893 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6158. Min Range: -4.6158
Max Act: 4.5221. Min Act: -0.1700
Data Index: 4941159 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6158. Min Range: -4.6158
Max Act: 4.5221. Min Act: -0.1699
Data Index: 1415032 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6158. Min Range: -4.6158
Max Act: 4.5221. Min Act: -0.1700
Data Index: 1138778 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6158. Min Range: -4.6158
Max Act: 4.5221. Min Act: -0.1700
Data Index: 4865482 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6158. Min Range: -4.6158
Max Act: 4.5221. Min Act: -0.1700
Data Index: 4342102 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6158. Min Range: -4.6158
Max Act: 4.5221. Min Act: -0.1700
Data Index: 850686 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6158. Min Range: -4.6158
Max Act: 4.5221. Min Act: -0.1700
Data Index: 4810154 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6158. Min Range: -4.6158
Max Act: 4.5221. Min Act: -0.1700
Data Index: 1921954 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6158. Min Range: -4.6158
Max Act: 4.5221. Min Act: -0.1700
Data Index: 3890261 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6158. Min Range: -4.6158
Max Act: 4.5221. Min Act: -0.1700
Data Index: 4379270 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6158. Min Range: -4.6158
Max Act: 4.5221. Min Act: -0.1700
Data Index: 257833 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6158. Min Range: -4.6158
Max Act: 4.5221. Min Act: -0.1700
Data Index: 535219 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6158. Min Range: -4.6158
Max Act: 4.5221. Min Act: -0.1700
Data Index: 1716498 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6158. Min Range: -4.6158
Max Act: 4.5221. Min Act: -0.1700
Data Index: 102322 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6158. Min Range: -4.6158
Max Act: 4.5221. Min Act: -0.1700
Data Index: 2269185 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6158. Min Range: -4.6158
Max Act: 4.5221. Min Act: -0.1700
Data Index: 1617815 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19