Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3644 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9245. Min Range: -4.9245
Max Act: 4.9245. Min Act: -0.1700
Data Index: 6182591 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9245. Min Range: -4.9245
Max Act: 4.8308. Min Act: -0.1700
Data Index: 2008795 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9245. Min Range: -4.9245
Max Act: 4.8308. Min Act: -0.1700
Data Index: 8246702 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9245. Min Range: -4.9245
Max Act: 4.7995. Min Act: -0.1700
Data Index: 6553383 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9245. Min Range: -4.9245
Max Act: 4.7995. Min Act: -0.1700
Data Index: 6071307 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9245. Min Range: -4.9245
Max Act: 4.7995. Min Act: -0.1700
Data Index: 2691270 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9245. Min Range: -4.9245
Max Act: 4.7370. Min Act: -0.1700
Data Index: 1178120 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9245. Min Range: -4.9245
Max Act: 4.7683. Min Act: -0.1700
Data Index: 582530 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9245. Min Range: -4.9245
Max Act: 4.7683. Min Act: -0.1700
Data Index: 7053266 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9245. Min Range: -4.9245
Max Act: 4.7058. Min Act: -0.1700
Data Index: 2281123 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9245. Min Range: -4.9245
Max Act: 4.7370. Min Act: -0.1700
Data Index: 7239037 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9245. Min Range: -4.9245
Max Act: 4.7058. Min Act: -0.1700
Data Index: 6667723 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9245. Min Range: -4.9245
Max Act: 4.7058. Min Act: -0.1700
Data Index: 6062076 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9245. Min Range: -4.9245
Max Act: 4.7058. Min Act: -0.1700
Data Index: 888129 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9245. Min Range: -4.9245
Max Act: 4.7058. Min Act: -0.1700
Data Index: 7438041 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9245. Min Range: -4.9245
Max Act: 4.7058. Min Act: -0.1700
Data Index: 4758679 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9245. Min Range: -4.9245
Max Act: 4.6745. Min Act: -0.1700
Data Index: 4759570 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9245. Min Range: -4.9245
Max Act: 4.6745. Min Act: -0.1700
Data Index: 703052 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9245. Min Range: -4.9245
Max Act: 4.6745. Min Act: -0.1700
Data Index: 6533592 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9245. Min Range: -4.9245
Max Act: 4.6745. Min Act: -0.1700
Data Index: 3473201 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19