Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5299 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7888. Min Range: -3.7888
Max Act: 3.7888. Min Act: -0.1498
Data Index: 4112629 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7888. Min Range: -3.7888
Max Act: 3.7419. Min Act: -0.1352
Data Index: 6255836 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7888. Min Range: -3.7888
Max Act: 3.7419. Min Act: -0.1138
Data Index: 949725 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7888. Min Range: -3.7888
Max Act: 3.7106. Min Act: -0.1628
Data Index: 7347371 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7888. Min Range: -3.7888
Max Act: 3.6950. Min Act: -0.1492
Data Index: 3265798 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7888. Min Range: -3.7888
Max Act: 3.6637. Min Act: -0.1391
Data Index: 4784845 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7888. Min Range: -3.7888
Max Act: 3.6324. Min Act: -0.1679
Data Index: 2997194 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7888. Min Range: -3.7888
Max Act: 3.6480. Min Act: -0.1480
Data Index: 1431818 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7888. Min Range: -3.7888
Max Act: 3.6637. Min Act: -0.1391
Data Index: 6103169 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7888. Min Range: -3.7888
Max Act: 3.6480. Min Act: -0.1606
Data Index: 2851925 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7888. Min Range: -3.7888
Max Act: 3.6480. Min Act: -0.1606
Data Index: 6437743 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7888. Min Range: -3.7888
Max Act: 3.6480. Min Act: -0.1368
Data Index: 3204139 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7888. Min Range: -3.7888
Max Act: 3.6324. Min Act: -0.1653
Data Index: 6671037 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7888. Min Range: -3.7888
Max Act: 3.6324. Min Act: -0.1676
Data Index: 1875717 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7888. Min Range: -3.7888
Max Act: 3.6167. Min Act: -0.1179
Data Index: 728841 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7888. Min Range: -3.7888
Max Act: 3.6480. Min Act: -0.1383
Data Index: 1876232 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7888. Min Range: -3.7888
Max Act: 3.6167. Min Act: -0.1691
Data Index: 1385512 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7888. Min Range: -3.7888
Max Act: 3.6324. Min Act: -0.1480
Data Index: 6414756 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7888. Min Range: -3.7888
Max Act: 3.6480. Min Act: -0.1266
Data Index: 7543080 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7888. Min Range: -3.7888
Max Act: 3.6324. Min Act: -0.1527
Data Index: 6114236 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #19