Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2706 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9183. Min Range: -4.9183
Max Act: 4.9183. Min Act: -0.1700
Data Index: 3973443 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9183. Min Range: -4.9183
Max Act: 4.9183. Min Act: -0.1700
Data Index: 7556573 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9183. Min Range: -4.9183
Max Act: 4.8558. Min Act: -0.1700
Data Index: 2486672 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9183. Min Range: -4.9183
Max Act: 4.8558. Min Act: -0.1700
Data Index: 2486671 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9183. Min Range: -4.9183
Max Act: 4.8246. Min Act: -0.1700
Data Index: 973941 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9183. Min Range: -4.9183
Max Act: 4.7933. Min Act: -0.1700
Data Index: 6547727 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9183. Min Range: -4.9183
Max Act: 4.7308. Min Act: -0.1700
Data Index: 8212367 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9183. Min Range: -4.9183
Max Act: 4.6996. Min Act: -0.1700
Data Index: 7872868 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9183. Min Range: -4.9183
Max Act: 4.7308. Min Act: -0.1700
Data Index: 5821485 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9183. Min Range: -4.9183
Max Act: 4.6683. Min Act: -0.1700
Data Index: 8212095 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9183. Min Range: -4.9183
Max Act: 4.6683. Min Act: -0.1700
Data Index: 7919725 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9183. Min Range: -4.9183
Max Act: 4.6996. Min Act: -0.1700
Data Index: 370072 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9183. Min Range: -4.9183
Max Act: 4.6683. Min Act: -0.1700
Data Index: 5982320 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9183. Min Range: -4.9183
Max Act: 4.6683. Min Act: -0.1700
Data Index: 4103357 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9183. Min Range: -4.9183
Max Act: 4.6683. Min Act: -0.1700
Data Index: 1752877 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9183. Min Range: -4.9183
Max Act: 4.6371. Min Act: -0.1700
Data Index: 2046813 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9183. Min Range: -4.9183
Max Act: 4.5746. Min Act: -0.1700
Data Index: 2719900 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9183. Min Range: -4.9183
Max Act: 4.6058. Min Act: -0.1700
Data Index: 5576149 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9183. Min Range: -4.9183
Max Act: 4.5746. Min Act: -0.1700
Data Index: 427517 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9183. Min Range: -4.9183
Max Act: 4.6058. Min Act: -0.1700
Data Index: 4357168 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #19