Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3625 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4197. Min Range: -5.4197
Max Act: 5.4197. Min Act: -0.1700
Data Index: 4212427 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4197. Min Range: -5.4197
Max Act: 5.3572. Min Act: -0.1700
Data Index: 4715048 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4197. Min Range: -5.4197
Max Act: 5.3259. Min Act: -0.1700
Data Index: 4470344 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4197. Min Range: -5.4197
Max Act: 5.2947. Min Act: -0.1700
Data Index: 2796207 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4197. Min Range: -5.4197
Max Act: 5.2947. Min Act: -0.1700
Data Index: 848016 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4197. Min Range: -5.4197
Max Act: 5.2634. Min Act: -0.1700
Data Index: 5935608 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4197. Min Range: -5.4197
Max Act: 5.2322. Min Act: -0.1699
Data Index: 6810006 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4197. Min Range: -5.4197
Max Act: 5.2322. Min Act: -0.1700
Data Index: 3221896 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4197. Min Range: -5.4197
Max Act: 5.2009. Min Act: -0.1700
Data Index: 5359184 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4197. Min Range: -5.4197
Max Act: 5.2322. Min Act: -0.1700
Data Index: 3351535 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4197. Min Range: -5.4197
Max Act: 5.2009. Min Act: -0.1700
Data Index: 454437 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4197. Min Range: -5.4197
Max Act: 5.2009. Min Act: -0.1700
Data Index: 3699552 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4197. Min Range: -5.4197
Max Act: 5.2009. Min Act: -0.1700
Data Index: 4506889 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4197. Min Range: -5.4197
Max Act: 5.2009. Min Act: -0.1700
Data Index: 8130055 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4197. Min Range: -5.4197
Max Act: 5.2009. Min Act: -0.1700
Data Index: 2499989 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4197. Min Range: -5.4197
Max Act: 5.1697. Min Act: -0.1700
Data Index: 8228658 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4197. Min Range: -5.4197
Max Act: 5.1697. Min Act: -0.1700
Data Index: 2492781 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4197. Min Range: -5.4197
Max Act: 5.1697. Min Act: -0.1700
Data Index: 7316517 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4197. Min Range: -5.4197
Max Act: 5.1697. Min Act: -0.1700
Data Index: 3054826 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4197. Min Range: -5.4197
Max Act: 5.2009. Min Act: -0.1700
Data Index: 6628038 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #19