Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 767 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6754. Min Range: -3.6754
Max Act: 3.6754. Min Act: -0.1700
Data Index: 7710742 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6754. Min Range: -3.6754
Max Act: 3.6754. Min Act: -0.1700
Data Index: 3469814 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6754. Min Range: -3.6754
Max Act: 3.5502. Min Act: -0.1700
Data Index: 1731227 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6754. Min Range: -3.6754
Max Act: 3.5345. Min Act: -0.1700
Data Index: 1033918 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6754. Min Range: -3.6754
Max Act: 3.5188. Min Act: -0.1700
Data Index: 2312228 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6754. Min Range: -3.6754
Max Act: 3.4405. Min Act: -0.1700
Data Index: 5715961 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6754. Min Range: -3.6754
Max Act: 3.4562. Min Act: -0.1700
Data Index: 3765100 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6754. Min Range: -3.6754
Max Act: 3.4248. Min Act: -0.1700
Data Index: 5639754 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6754. Min Range: -3.6754
Max Act: 3.4248. Min Act: -0.1700
Data Index: 1816019 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6754. Min Range: -3.6754
Max Act: 3.4248. Min Act: -0.1700
Data Index: 3365180 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6754. Min Range: -3.6754
Max Act: 3.4248. Min Act: -0.1700
Data Index: 4061589 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6754. Min Range: -3.6754
Max Act: 3.4248. Min Act: -0.1700
Data Index: 7334883 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6754. Min Range: -3.6754
Max Act: 3.3935. Min Act: -0.1700
Data Index: 1803285 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6754. Min Range: -3.6754
Max Act: 3.3935. Min Act: -0.1700
Data Index: 1571592 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6754. Min Range: -3.6754
Max Act: 3.3778. Min Act: -0.1700
Data Index: 2883709 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6754. Min Range: -3.6754
Max Act: 3.3621. Min Act: -0.1700
Data Index: 3479123 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6754. Min Range: -3.6754
Max Act: 3.3778. Min Act: -0.1700
Data Index: 3617280 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6754. Min Range: -3.6754
Max Act: 3.3621. Min Act: -0.1700
Data Index: 6463784 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6754. Min Range: -3.6754
Max Act: 3.3464. Min Act: -0.1700
Data Index: 6006968 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6754. Min Range: -3.6754
Max Act: 3.3621. Min Act: -0.1700
Data Index: 1867160 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19