Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3770 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5900. Min Range: -4.5900
Max Act: 4.5900. Min Act: -0.1700
Data Index: 4414514 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5900. Min Range: -4.5900
Max Act: 4.4649. Min Act: -0.1700
Data Index: 4025748 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5900. Min Range: -4.5900
Max Act: 4.4649. Min Act: -0.1700
Data Index: 8176021 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5900. Min Range: -4.5900
Max Act: 4.4649. Min Act: -0.1700
Data Index: 124882 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5900. Min Range: -4.5900
Max Act: 4.4649. Min Act: -0.1700
Data Index: 1323090 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5900. Min Range: -4.5900
Max Act: 4.4649. Min Act: -0.1700
Data Index: 3266591 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5900. Min Range: -4.5900
Max Act: 4.4337. Min Act: -0.1700
Data Index: 116200 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5900. Min Range: -4.5900
Max Act: 4.4649. Min Act: -0.1700
Data Index: 5890902 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5900. Min Range: -4.5900
Max Act: 4.4337. Min Act: -0.1700
Data Index: 3143427 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5900. Min Range: -4.5900
Max Act: 4.4337. Min Act: -0.1700
Data Index: 8698034 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5900. Min Range: -4.5900
Max Act: 4.4649. Min Act: -0.1700
Data Index: 3032733 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5900. Min Range: -4.5900
Max Act: 4.4337. Min Act: -0.1700
Data Index: 4660921 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5900. Min Range: -4.5900
Max Act: 4.4024. Min Act: -0.1700
Data Index: 327096 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5900. Min Range: -4.5900
Max Act: 4.4337. Min Act: -0.1700
Data Index: 8213945 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5900. Min Range: -4.5900
Max Act: 4.4024. Min Act: -0.1700
Data Index: 7400814 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5900. Min Range: -4.5900
Max Act: 4.3712. Min Act: -0.1700
Data Index: 7563845 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5900. Min Range: -4.5900
Max Act: 4.3712. Min Act: -0.1700
Data Index: 5198837 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5900. Min Range: -4.5900
Max Act: 4.3712. Min Act: -0.1700
Data Index: 8150007 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5900. Min Range: -4.5900
Max Act: 4.3712. Min Act: -0.1700
Data Index: 6261652 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5900. Min Range: -4.5900
Max Act: 4.2774. Min Act: -0.1700
Data Index: 6363470 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #19