Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2590 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8736. Min Range: -5.8736
Max Act: 5.8736. Min Act: -0.1700
Data Index: 3048343 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8736. Min Range: -5.8736
Max Act: 5.8423. Min Act: -0.1700
Data Index: 4458907 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8736. Min Range: -5.8736
Max Act: 5.7173. Min Act: -0.1700
Data Index: 7747361 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8736. Min Range: -5.8736
Max Act: 5.6861. Min Act: -0.1700
Data Index: 925509 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8736. Min Range: -5.8736
Max Act: 5.6861. Min Act: -0.1700
Data Index: 2523032 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8736. Min Range: -5.8736
Max Act: 5.6548. Min Act: -0.1700
Data Index: 5634490 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8736. Min Range: -5.8736
Max Act: 5.6236. Min Act: -0.1700
Data Index: 7506209 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8736. Min Range: -5.8736
Max Act: 5.6236. Min Act: -0.1700
Data Index: 5731248 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8736. Min Range: -5.8736
Max Act: 5.6236. Min Act: -0.1700
Data Index: 6165954 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8736. Min Range: -5.8736
Max Act: 5.5923. Min Act: -0.1700
Data Index: 7562104 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8736. Min Range: -5.8736
Max Act: 5.5923. Min Act: -0.1700
Data Index: 5865536 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8736. Min Range: -5.8736
Max Act: 5.5923. Min Act: -0.1700
Data Index: 5747177 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8736. Min Range: -5.8736
Max Act: 5.5923. Min Act: -0.1700
Data Index: 122654 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8736. Min Range: -5.8736
Max Act: 5.5923. Min Act: -0.1700
Data Index: 7784446 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8736. Min Range: -5.8736
Max Act: 5.5923. Min Act: -0.1700
Data Index: 632498 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8736. Min Range: -5.8736
Max Act: 5.5611. Min Act: -0.1700
Data Index: 3781364 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8736. Min Range: -5.8736
Max Act: 5.5298. Min Act: -0.1700
Data Index: 6054668 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8736. Min Range: -5.8736
Max Act: 5.5611. Min Act: -0.1700
Data Index: 6831364 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8736. Min Range: -5.8736
Max Act: 5.5298. Min Act: -0.1700
Data Index: 497638 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8736. Min Range: -5.8736
Max Act: 5.5298. Min Act: -0.1700
Data Index: 2842288 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19