Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2066 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2486. Min Range: -5.2486
Max Act: 5.2486. Min Act: -0.1700
Data Index: 2123463 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2486. Min Range: -5.2486
Max Act: 5.2486. Min Act: -0.1700
Data Index: 6959523 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2486. Min Range: -5.2486
Max Act: 5.2486. Min Act: -0.1700
Data Index: 4115636 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2486. Min Range: -5.2486
Max Act: 5.1861. Min Act: -0.1700
Data Index: 6929791 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2486. Min Range: -5.2486
Max Act: 5.1861. Min Act: -0.1700
Data Index: 4021303 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2486. Min Range: -5.2486
Max Act: 5.1548. Min Act: -0.1700
Data Index: 8408259 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2486. Min Range: -5.2486
Max Act: 5.1861. Min Act: -0.1700
Data Index: 8424122 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2486. Min Range: -5.2486
Max Act: 5.1861. Min Act: -0.1700
Data Index: 5849771 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2486. Min Range: -5.2486
Max Act: 5.1236. Min Act: -0.1700
Data Index: 3924548 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2486. Min Range: -5.2486
Max Act: 5.1548. Min Act: -0.1700
Data Index: 8353365 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2486. Min Range: -5.2486
Max Act: 5.1236. Min Act: -0.1700
Data Index: 1190806 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2486. Min Range: -5.2486
Max Act: 5.1548. Min Act: -0.1700
Data Index: 6778169 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2486. Min Range: -5.2486
Max Act: 5.1236. Min Act: -0.1700
Data Index: 5069016 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2486. Min Range: -5.2486
Max Act: 5.1236. Min Act: -0.1700
Data Index: 1475660 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2486. Min Range: -5.2486
Max Act: 5.1236. Min Act: -0.1700
Data Index: 8103 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2486. Min Range: -5.2486
Max Act: 5.1236. Min Act: -0.1700
Data Index: 406070 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2486. Min Range: -5.2486
Max Act: 5.1236. Min Act: -0.1700
Data Index: 5297599 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2486. Min Range: -5.2486
Max Act: 5.0923. Min Act: -0.1700
Data Index: 5826263 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2486. Min Range: -5.2486
Max Act: 5.0923. Min Act: -0.1700
Data Index: 2806115 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2486. Min Range: -5.2486
Max Act: 5.1236. Min Act: -0.1700
Data Index: 6172783 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19