Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6123 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4606. Min Range: -6.4606
Max Act: 6.4606. Min Act: -0.1700
Data Index: 2488237 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4606. Min Range: -6.4606
Max Act: 6.4293. Min Act: -0.1700
Data Index: 4276409 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4606. Min Range: -6.4606
Max Act: 6.3356. Min Act: -0.1700
Data Index: 7647588 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4606. Min Range: -6.4606
Max Act: 6.2106. Min Act: -0.1700
Data Index: 7081002 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4606. Min Range: -6.4606
Max Act: 6.1793. Min Act: -0.1700
Data Index: 7647576 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4606. Min Range: -6.4606
Max Act: 6.1793. Min Act: -0.1700
Data Index: 4934249 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4606. Min Range: -6.4606
Max Act: 6.1168. Min Act: -0.1700
Data Index: 2193262 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4606. Min Range: -6.4606
Max Act: 6.1168. Min Act: -0.1700
Data Index: 785678 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4606. Min Range: -6.4606
Max Act: 6.1168. Min Act: -0.1700
Data Index: 3831194 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4606. Min Range: -6.4606
Max Act: 6.0856. Min Act: -0.1700
Data Index: 1026893 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4606. Min Range: -6.4606
Max Act: 6.0543. Min Act: -0.1700
Data Index: 7647587 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4606. Min Range: -6.4606
Max Act: 6.0231. Min Act: -0.1700
Data Index: 1828440 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4606. Min Range: -6.4606
Max Act: 6.0231. Min Act: -0.1700
Data Index: 4306939 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4606. Min Range: -6.4606
Max Act: 5.9293. Min Act: -0.1700
Data Index: 992032 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4606. Min Range: -6.4606
Max Act: 5.8981. Min Act: -0.1700
Data Index: 7647593 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4606. Min Range: -6.4606
Max Act: 5.8981. Min Act: -0.1700
Data Index: 785677 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4606. Min Range: -6.4606
Max Act: 5.8668. Min Act: -0.1700
Data Index: 8328108 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4606. Min Range: -6.4606
Max Act: 5.8356. Min Act: -0.1700
Data Index: 431814 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4606. Min Range: -6.4606
Max Act: 5.8043. Min Act: -0.1700
Data Index: 202869 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4606. Min Range: -6.4606
Max Act: 5.8043. Min Act: -0.1700
Data Index: 1660512 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19