Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2879 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9912. Min Range: -3.9912
Max Act: 3.9912. Min Act: -0.1700
Data Index: 1531633 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9912. Min Range: -3.9912
Max Act: 3.9912. Min Act: -0.1700
Data Index: 7444466 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9912. Min Range: -3.9912
Max Act: 3.9287. Min Act: -0.1700
Data Index: 7047579 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9912. Min Range: -3.9912
Max Act: 3.8662. Min Act: -0.1700
Data Index: 3479489 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9912. Min Range: -3.9912
Max Act: 3.8975. Min Act: -0.1700
Data Index: 1809439 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9912. Min Range: -3.9912
Max Act: 3.8349. Min Act: -0.1700
Data Index: 909221 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9912. Min Range: -3.9912
Max Act: 3.8036. Min Act: -0.1700
Data Index: 7047572 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9912. Min Range: -3.9912
Max Act: 3.7724. Min Act: -0.1700
Data Index: 1033472 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9912. Min Range: -3.9912
Max Act: 3.7411. Min Act: -0.1700
Data Index: 346056 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9912. Min Range: -3.9912
Max Act: 3.7411. Min Act: -0.1700
Data Index: 3956078 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9912. Min Range: -3.9912
Max Act: 3.6785. Min Act: -0.1700
Data Index: 1837758 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9912. Min Range: -3.9912
Max Act: 3.6785. Min Act: -0.1700
Data Index: 3174171 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9912. Min Range: -3.9912
Max Act: 3.6785. Min Act: -0.1700
Data Index: 6719762 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9912. Min Range: -3.9912
Max Act: 3.6629. Min Act: -0.1700
Data Index: 423974 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9912. Min Range: -3.9912
Max Act: 3.6629. Min Act: -0.1700
Data Index: 5802902 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9912. Min Range: -3.9912
Max Act: 3.6316. Min Act: -0.1700
Data Index: 250275 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9912. Min Range: -3.9912
Max Act: 3.6159. Min Act: -0.1700
Data Index: 6575105 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9912. Min Range: -3.9912
Max Act: 3.6159. Min Act: -0.1700
Data Index: 3376196 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9912. Min Range: -3.9912
Max Act: 3.6159. Min Act: -0.1700
Data Index: 6850981 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9912. Min Range: -3.9912
Max Act: 3.6003. Min Act: -0.1700
Data Index: 2788667 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #19