Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2870 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8371. Min Range: -3.8371
Max Act: 3.8371. Min Act: -0.1700
Data Index: 4133253 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8371. Min Range: -3.8371
Max Act: 3.7589. Min Act: -0.1700
Data Index: 5750280 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8371. Min Range: -3.8371
Max Act: 3.6337. Min Act: -0.1700
Data Index: 4387964 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8371. Min Range: -3.8371
Max Act: 3.6181. Min Act: -0.1700
Data Index: 4055005 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8371. Min Range: -3.8371
Max Act: 3.6181. Min Act: -0.1700
Data Index: 2656276 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8371. Min Range: -3.8371
Max Act: 3.5555. Min Act: -0.1700
Data Index: 923639 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8371. Min Range: -3.8371
Max Act: 3.5555. Min Act: -0.1700
Data Index: 6522692 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8371. Min Range: -3.8371
Max Act: 3.5398. Min Act: -0.1700
Data Index: 5037027 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8371. Min Range: -3.8371
Max Act: 3.5242. Min Act: -0.1700
Data Index: 4614823 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8371. Min Range: -3.8371
Max Act: 3.5398. Min Act: -0.1700
Data Index: 6376849 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8371. Min Range: -3.8371
Max Act: 3.5398. Min Act: -0.1700
Data Index: 1323865 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8371. Min Range: -3.8371
Max Act: 3.5242. Min Act: -0.1700
Data Index: 4213858 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8371. Min Range: -3.8371
Max Act: 3.5398. Min Act: -0.1700
Data Index: 4275395 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8371. Min Range: -3.8371
Max Act: 3.5242. Min Act: -0.1700
Data Index: 581945 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8371. Min Range: -3.8371
Max Act: 3.5085. Min Act: -0.1700
Data Index: 4572477 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8371. Min Range: -3.8371
Max Act: 3.5242. Min Act: -0.1700
Data Index: 8621393 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8371. Min Range: -3.8371
Max Act: 3.5085. Min Act: -0.1700
Data Index: 6177422 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8371. Min Range: -3.8371
Max Act: 3.5085. Min Act: -0.1700
Data Index: 5236655 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8371. Min Range: -3.8371
Max Act: 3.4928. Min Act: -0.1700
Data Index: 5035741 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8371. Min Range: -3.8371
Max Act: 3.4928. Min Act: -0.1700
Data Index: 1424865 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #19