Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3505 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0516. Min Range: -5.0516
Max Act: 5.0203. Min Act: -0.1700
Data Index: 7144912 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0516. Min Range: -5.0516
Max Act: 5.0516. Min Act: -0.1700
Data Index: 3755904 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.8953. Min Act: -0.1700
Data Index: 7036712 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.8953. Min Act: -0.1700
Data Index: 280467 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.8953. Min Act: -0.1700
Data Index: 6298975 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.8641. Min Act: -0.1700
Data Index: 1700459 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.8641. Min Act: -0.1700
Data Index: 3029259 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.8641. Min Act: -0.1700
Data Index: 7655745 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.8641. Min Act: -0.1700
Data Index: 1390155 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.8641. Min Act: -0.1700
Data Index: 6687778 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.8328. Min Act: -0.1700
Data Index: 6289694 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.8016. Min Act: -0.1700
Data Index: 5960542 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.8016. Min Act: -0.1700
Data Index: 163240 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.7703. Min Act: -0.1700
Data Index: 6634225 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.7703. Min Act: -0.1700
Data Index: 4828932 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.7703. Min Act: -0.1700
Data Index: 2553942 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.7703. Min Act: -0.1700
Data Index: 6021567 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.7703. Min Act: -0.1700
Data Index: 8035829 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.7703. Min Act: -0.1700
Data Index: 8780580 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.7391. Min Act: -0.1700
Data Index: 2513037 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #19