Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1482 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9299. Min Range: -3.9299
Max Act: 3.9299. Min Act: -0.1700
Data Index: 6441388 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9299. Min Range: -3.9299
Max Act: 3.8674. Min Act: -0.1700
Data Index: 3537072 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9299. Min Range: -3.9299
Max Act: 3.8674. Min Act: -0.1700
Data Index: 7576440 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9299. Min Range: -3.9299
Max Act: 3.8674. Min Act: -0.1700
Data Index: 783066 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9299. Min Range: -3.9299
Max Act: 3.8674. Min Act: -0.1700
Data Index: 290947 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9299. Min Range: -3.9299
Max Act: 3.8361. Min Act: -0.1700
Data Index: 2311065 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9299. Min Range: -3.9299
Max Act: 3.8361. Min Act: -0.1700
Data Index: 8570366 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9299. Min Range: -3.9299
Max Act: 3.8361. Min Act: -0.1700
Data Index: 5803273 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9299. Min Range: -3.9299
Max Act: 3.8361. Min Act: -0.1700
Data Index: 4882942 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9299. Min Range: -3.9299
Max Act: 3.8049. Min Act: -0.1700
Data Index: 1302967 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9299. Min Range: -3.9299
Max Act: 3.8049. Min Act: -0.1700
Data Index: 2508703 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9299. Min Range: -3.9299
Max Act: 3.8049. Min Act: -0.1700
Data Index: 3076468 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9299. Min Range: -3.9299
Max Act: 3.7736. Min Act: -0.1700
Data Index: 7459248 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9299. Min Range: -3.9299
Max Act: 3.7736. Min Act: -0.1700
Data Index: 4833354 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9299. Min Range: -3.9299
Max Act: 3.7423. Min Act: -0.1700
Data Index: 1234718 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9299. Min Range: -3.9299
Max Act: 3.7423. Min Act: -0.1700
Data Index: 4951918 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9299. Min Range: -3.9299
Max Act: 3.7423. Min Act: -0.1700
Data Index: 4542435 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9299. Min Range: -3.9299
Max Act: 3.7110. Min Act: -0.1700
Data Index: 2012281 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9299. Min Range: -3.9299
Max Act: 3.7110. Min Act: -0.1700
Data Index: 871431 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9299. Min Range: -3.9299
Max Act: 3.7110. Min Act: -0.1700
Data Index: 4319595 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19