Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 680 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6828. Min Range: -5.6828
Max Act: 5.6828. Min Act: -0.1700
Data Index: 869179 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6828. Min Range: -5.6828
Max Act: 5.4953. Min Act: -0.1700
Data Index: 5402864 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6828. Min Range: -5.6828
Max Act: 5.4328. Min Act: -0.1700
Data Index: 6219615 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6828. Min Range: -5.6828
Max Act: 5.4328. Min Act: -0.1700
Data Index: 5482075 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6828. Min Range: -5.6828
Max Act: 5.4015. Min Act: -0.1700
Data Index: 5366734 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6828. Min Range: -5.6828
Max Act: 5.4015. Min Act: -0.1700
Data Index: 5256660 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6828. Min Range: -5.6828
Max Act: 5.3703. Min Act: -0.1700
Data Index: 361831 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6828. Min Range: -5.6828
Max Act: 5.3703. Min Act: -0.1700
Data Index: 358152 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6828. Min Range: -5.6828
Max Act: 5.3703. Min Act: -0.1700
Data Index: 8463477 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6828. Min Range: -5.6828
Max Act: 5.3390. Min Act: -0.1700
Data Index: 4890442 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6828. Min Range: -5.6828
Max Act: 5.3390. Min Act: -0.1700
Data Index: 4696401 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6828. Min Range: -5.6828
Max Act: 5.3078. Min Act: -0.1700
Data Index: 6219463 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6828. Min Range: -5.6828
Max Act: 5.2765. Min Act: -0.1700
Data Index: 5080080 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6828. Min Range: -5.6828
Max Act: 5.2765. Min Act: -0.1700
Data Index: 4276566 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6828. Min Range: -5.6828
Max Act: 5.2765. Min Act: -0.1700
Data Index: 2406277 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6828. Min Range: -5.6828
Max Act: 5.2765. Min Act: -0.1700
Data Index: 5653190 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6828. Min Range: -5.6828
Max Act: 5.2765. Min Act: -0.1700
Data Index: 5396887 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6828. Min Range: -5.6828
Max Act: 5.2765. Min Act: -0.1700
Data Index: 345721 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6828. Min Range: -5.6828
Max Act: 5.2765. Min Act: -0.1700
Data Index: 465865 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6828. Min Range: -5.6828
Max Act: 5.2765. Min Act: -0.1700
Data Index: 2087857 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #19