Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2024 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8346. Min Range: -4.8346
Max Act: 4.8346. Min Act: -0.1700
Data Index: 1891834 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8346. Min Range: -4.8346
Max Act: 4.7721. Min Act: -0.1700
Data Index: 3388970 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8346. Min Range: -4.8346
Max Act: 4.6471. Min Act: -0.1700
Data Index: 5870937 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8346. Min Range: -4.8346
Max Act: 4.6471. Min Act: -0.1700
Data Index: 3096862 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8346. Min Range: -4.8346
Max Act: 4.6783. Min Act: -0.1700
Data Index: 470967 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8346. Min Range: -4.8346
Max Act: 4.6471. Min Act: -0.1700
Data Index: 4037576 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8346. Min Range: -4.8346
Max Act: 4.6158. Min Act: -0.1700
Data Index: 2700716 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8346. Min Range: -4.8346
Max Act: 4.5533. Min Act: -0.1700
Data Index: 4850466 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8346. Min Range: -4.8346
Max Act: 4.5533. Min Act: -0.1699
Data Index: 6279658 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8346. Min Range: -4.8346
Max Act: 4.5533. Min Act: -0.1700
Data Index: 1022487 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8346. Min Range: -4.8346
Max Act: 4.5533. Min Act: -0.1700
Data Index: 8002086 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8346. Min Range: -4.8346
Max Act: 4.5533. Min Act: -0.1700
Data Index: 548634 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8346. Min Range: -4.8346
Max Act: 4.5533. Min Act: -0.1700
Data Index: 521182 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8346. Min Range: -4.8346
Max Act: 4.5221. Min Act: -0.1700
Data Index: 4819281 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8346. Min Range: -4.8346
Max Act: 4.5221. Min Act: -0.1700
Data Index: 4314905 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8346. Min Range: -4.8346
Max Act: 4.5221. Min Act: -0.1700
Data Index: 625094 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8346. Min Range: -4.8346
Max Act: 4.5221. Min Act: -0.1700
Data Index: 1582588 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8346. Min Range: -4.8346
Max Act: 4.5221. Min Act: -0.1700
Data Index: 1665187 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8346. Min Range: -4.8346
Max Act: 4.5221. Min Act: -0.1697
Data Index: 5231972 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8346. Min Range: -4.8346
Max Act: 4.5221. Min Act: -0.1700
Data Index: 5934090 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #19