Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3921 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.6304. Min Act: -0.1700
Data Index: 2588750 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.6304. Min Act: -0.1700
Data Index: 1968290 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.5991. Min Act: -0.1700
Data Index: 7650708 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.5679. Min Act: -0.1700
Data Index: 5304695 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.5366. Min Act: -0.1700
Data Index: 8047408 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.5054. Min Act: -0.1700
Data Index: 7979919 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.5366. Min Act: -0.1700
Data Index: 2179783 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.5054. Min Act: -0.1700
Data Index: 3900399 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.4741. Min Act: -0.1700
Data Index: 2497808 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.4741. Min Act: -0.1700
Data Index: 2010619 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.4429. Min Act: -0.1700
Data Index: 3278013 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.4429. Min Act: -0.1700
Data Index: 5834410 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.4429. Min Act: -0.1700
Data Index: 954691 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.4429. Min Act: -0.1700
Data Index: 1269064 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.3804. Min Act: -0.1700
Data Index: 4439651 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.4116. Min Act: -0.1700
Data Index: 7273128 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.4116. Min Act: -0.1700
Data Index: 5475471 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.3804. Min Act: -0.1700
Data Index: 8282631 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.4116. Min Act: -0.1700
Data Index: 3711254 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.3491. Min Act: -0.1700
Data Index: 3609460 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #19