Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 254 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.1579. Min Range: -8.1579
Max Act: 8.1579. Min Act: -0.1700
Data Index: 5130444 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1579. Min Range: -8.1579
Max Act: 7.8767. Min Act: -0.1700
Data Index: 2182303 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1579. Min Range: -8.1579
Max Act: 7.6892. Min Act: -0.1700
Data Index: 4541445 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1579. Min Range: -8.1579
Max Act: 7.6579. Min Act: -0.1700
Data Index: 3046248 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1579. Min Range: -8.1579
Max Act: 7.6579. Min Act: -0.1700
Data Index: 8739115 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1579. Min Range: -8.1579
Max Act: 7.6267. Min Act: -0.1700
Data Index: 6594733 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1579. Min Range: -8.1579
Max Act: 7.5329. Min Act: -0.1700
Data Index: 1835335 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1579. Min Range: -8.1579
Max Act: 7.5329. Min Act: -0.1700
Data Index: 5966973 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1579. Min Range: -8.1579
Max Act: 7.5329. Min Act: -0.1700
Data Index: 4043995 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1579. Min Range: -8.1579
Max Act: 7.4704. Min Act: -0.1700
Data Index: 4225706 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1579. Min Range: -8.1579
Max Act: 7.5017. Min Act: -0.1700
Data Index: 6652055 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1579. Min Range: -8.1579
Max Act: 7.4704. Min Act: -0.1700
Data Index: 83613 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1579. Min Range: -8.1579
Max Act: 7.3767. Min Act: -0.1700
Data Index: 7371718 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1579. Min Range: -8.1579
Max Act: 7.3142. Min Act: -0.1700
Data Index: 7259532 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1579. Min Range: -8.1579
Max Act: 7.3454. Min Act: -0.1700
Data Index: 571945 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1579. Min Range: -8.1579
Max Act: 7.3454. Min Act: -0.1700
Data Index: 2694683 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1579. Min Range: -8.1579
Max Act: 7.3142. Min Act: -0.1700
Data Index: 3484438 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1579. Min Range: -8.1579
Max Act: 7.3454. Min Act: -0.1700
Data Index: 4323843 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1579. Min Range: -8.1579
Max Act: 7.3142. Min Act: -0.1700
Data Index: 1666010 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1579. Min Range: -8.1579
Max Act: 7.2829. Min Act: -0.1700
Data Index: 4635508 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #19