Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4696 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1661. Min Range: -4.1661
Max Act: 4.1661. Min Act: -0.1700
Data Index: 5760266 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1661. Min Range: -4.1661
Max Act: 4.0410. Min Act: -0.1700
Data Index: 4272823 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1661. Min Range: -4.1661
Max Act: 4.0723. Min Act: -0.1700
Data Index: 1671252 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1661. Min Range: -4.1661
Max Act: 4.0723. Min Act: -0.1700
Data Index: 4175999 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1661. Min Range: -4.1661
Max Act: 4.0410. Min Act: -0.1700
Data Index: 385711 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1661. Min Range: -4.1661
Max Act: 3.9785. Min Act: -0.1700
Data Index: 661269 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1661. Min Range: -4.1661
Max Act: 3.9785. Min Act: -0.1700
Data Index: 5277373 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1661. Min Range: -4.1661
Max Act: 3.9472. Min Act: -0.1700
Data Index: 7056157 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1661. Min Range: -4.1661
Max Act: 3.9785. Min Act: -0.1700
Data Index: 5069939 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1661. Min Range: -4.1661
Max Act: 3.9472. Min Act: -0.1700
Data Index: 1067797 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1661. Min Range: -4.1661
Max Act: 3.9160. Min Act: -0.1700
Data Index: 385712 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1661. Min Range: -4.1661
Max Act: 3.9160. Min Act: -0.1700
Data Index: 1061467 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1661. Min Range: -4.1661
Max Act: 3.9160. Min Act: -0.1700
Data Index: 2663458 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1661. Min Range: -4.1661
Max Act: 3.8534. Min Act: -0.1700
Data Index: 2814281 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1661. Min Range: -4.1661
Max Act: 3.8534. Min Act: -0.1700
Data Index: 970160 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1661. Min Range: -4.1661
Max Act: 3.8847. Min Act: -0.1700
Data Index: 2500394 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1661. Min Range: -4.1661
Max Act: 3.8222. Min Act: -0.1700
Data Index: 6313197 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1661. Min Range: -4.1661
Max Act: 3.8222. Min Act: -0.1700
Data Index: 4560541 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1661. Min Range: -4.1661
Max Act: 3.7909. Min Act: -0.1700
Data Index: 5369032 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1661. Min Range: -4.1661
Max Act: 3.7753. Min Act: -0.1700
Data Index: 1480201 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19