Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3366 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.8956. Min Range: -1.8956
Max Act: 1.8956. Min Act: -0.1700
Data Index: 2154944 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8956. Min Range: -1.8956
Max Act: 1.8614. Min Act: -0.1700
Data Index: 3970969 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8956. Min Range: -1.8956
Max Act: 1.8614. Min Act: -0.1700
Data Index: 8443891 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8956. Min Range: -1.8956
Max Act: 1.8614. Min Act: -0.1700
Data Index: 5850234 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8956. Min Range: -1.8956
Max Act: 1.8443. Min Act: -0.1700
Data Index: 7583866 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8956. Min Range: -1.8956
Max Act: 1.8271. Min Act: -0.1700
Data Index: 5882124 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8956. Min Range: -1.8956
Max Act: 1.8014. Min Act: -0.1700
Data Index: 1567098 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8956. Min Range: -1.8956
Max Act: 1.8100. Min Act: -0.1695
Data Index: 125312 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8956. Min Range: -1.8956
Max Act: 1.8100. Min Act: -0.1700
Data Index: 2542364 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8956. Min Range: -1.8956
Max Act: 1.8186. Min Act: -0.1700
Data Index: 750579 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8956. Min Range: -1.8956
Max Act: 1.8014. Min Act: -0.1700
Data Index: 2430184 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8956. Min Range: -1.8956
Max Act: 1.7928. Min Act: -0.1698
Data Index: 1497447 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8956. Min Range: -1.8956
Max Act: 1.7842. Min Act: -0.1700
Data Index: 6940715 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8956. Min Range: -1.8956
Max Act: 1.7928. Min Act: -0.1700
Data Index: 5648203 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8956. Min Range: -1.8956
Max Act: 1.7928. Min Act: -0.1700
Data Index: 4141774 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8956. Min Range: -1.8956
Max Act: 1.7755. Min Act: -0.1700
Data Index: 8008257 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8956. Min Range: -1.8956
Max Act: 1.7669. Min Act: -0.1700
Data Index: 5342759 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8956. Min Range: -1.8956
Max Act: 1.7496. Min Act: -0.1700
Data Index: 5529261 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8956. Min Range: -1.8956
Max Act: 1.7583. Min Act: -0.1700
Data Index: 2021379 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8956. Min Range: -1.8956
Max Act: 1.7496. Min Act: -0.1700
Data Index: 3440068 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #19