Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 315 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8745. Min Range: -6.8745
Max Act: 6.8745. Min Act: -0.1700
Data Index: 1586664 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8745. Min Range: -6.8745
Max Act: 6.2182. Min Act: -0.1700
Data Index: 4009245 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8745. Min Range: -6.8745
Max Act: 6.1870. Min Act: -0.1700
Data Index: 2903206 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8745. Min Range: -6.8745
Max Act: 6.1557. Min Act: -0.1700
Data Index: 5797566 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8745. Min Range: -6.8745
Max Act: 6.1245. Min Act: -0.1700
Data Index: 7919900 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8745. Min Range: -6.8745
Max Act: 6.1245. Min Act: -0.1700
Data Index: 2488173 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8745. Min Range: -6.8745
Max Act: 6.0932. Min Act: -0.1700
Data Index: 992574 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8745. Min Range: -6.8745
Max Act: 6.0932. Min Act: -0.1700
Data Index: 764308 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8745. Min Range: -6.8745
Max Act: 6.0620. Min Act: -0.1700
Data Index: 2249070 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8745. Min Range: -6.8745
Max Act: 6.0307. Min Act: -0.1700
Data Index: 3421309 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8745. Min Range: -6.8745
Max Act: 6.0620. Min Act: -0.1700
Data Index: 3923681 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8745. Min Range: -6.8745
Max Act: 6.0932. Min Act: -0.1700
Data Index: 4900805 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8745. Min Range: -6.8745
Max Act: 6.0307. Min Act: -0.1700
Data Index: 5127619 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8745. Min Range: -6.8745
Max Act: 5.9682. Min Act: -0.1700
Data Index: 4131991 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8745. Min Range: -6.8745
Max Act: 5.9682. Min Act: -0.1700
Data Index: 5520486 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8745. Min Range: -6.8745
Max Act: 5.9682. Min Act: -0.1700
Data Index: 2366462 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8745. Min Range: -6.8745
Max Act: 5.9370. Min Act: -0.1700
Data Index: 6904346 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8745. Min Range: -6.8745
Max Act: 5.8745. Min Act: -0.1700
Data Index: 5005690 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8745. Min Range: -6.8745
Max Act: 5.9057. Min Act: -0.1700
Data Index: 150299 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8745. Min Range: -6.8745
Max Act: 5.9057. Min Act: -0.1700
Data Index: 4737811 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #19