Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2168 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.9175. Min Range: -8.9175
Max Act: 8.9175. Min Act: -0.1700
Data Index: 6930678 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9175. Min Range: -8.9175
Max Act: 8.9175. Min Act: -0.1700
Data Index: 6394813 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9175. Min Range: -8.9175
Max Act: 8.8550. Min Act: -0.1700
Data Index: 1847066 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9175. Min Range: -8.9175
Max Act: 8.7925. Min Act: -0.1700
Data Index: 7418432 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9175. Min Range: -8.9175
Max Act: 8.7925. Min Act: -0.1700
Data Index: 5845300 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9175. Min Range: -8.9175
Max Act: 8.7925. Min Act: -0.1700
Data Index: 8306241 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9175. Min Range: -8.9175
Max Act: 8.7925. Min Act: -0.1700
Data Index: 4099805 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9175. Min Range: -8.9175
Max Act: 8.7300. Min Act: -0.1700
Data Index: 8430699 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9175. Min Range: -8.9175
Max Act: 8.7925. Min Act: -0.1700
Data Index: 7045284 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9175. Min Range: -8.9175
Max Act: 8.7925. Min Act: -0.1700
Data Index: 2767218 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9175. Min Range: -8.9175
Max Act: 8.7300. Min Act: -0.1700
Data Index: 5469513 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9175. Min Range: -8.9175
Max Act: 8.6675. Min Act: -0.1700
Data Index: 5521579 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9175. Min Range: -8.9175
Max Act: 8.7300. Min Act: -0.1700
Data Index: 2142336 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9175. Min Range: -8.9175
Max Act: 8.7300. Min Act: -0.1700
Data Index: 2140124 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9175. Min Range: -8.9175
Max Act: 8.7300. Min Act: -0.1700
Data Index: 1495198 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9175. Min Range: -8.9175
Max Act: 8.6675. Min Act: -0.1700
Data Index: 6956765 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9175. Min Range: -8.9175
Max Act: 8.6675. Min Act: -0.1700
Data Index: 2550667 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9175. Min Range: -8.9175
Max Act: 8.6675. Min Act: -0.1700
Data Index: 1768037 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9175. Min Range: -8.9175
Max Act: 8.6675. Min Act: -0.1700
Data Index: 4220455 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9175. Min Range: -8.9175
Max Act: 8.6675. Min Act: -0.1700
Data Index: 4119080 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #19