Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2478 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2517. Min Range: -7.2517
Max Act: 7.2517. Min Act: -0.1700
Data Index: 2195642 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2517. Min Range: -7.2517
Max Act: 6.2517. Min Act: -0.1700
Data Index: 6787664 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2517. Min Range: -7.2517
Max Act: 6.1580. Min Act: -0.1700
Data Index: 8576357 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2517. Min Range: -7.2517
Max Act: 6.1580. Min Act: -0.1700
Data Index: 846605 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2517. Min Range: -7.2517
Max Act: 6.0642. Min Act: -0.1700
Data Index: 8576360 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2517. Min Range: -7.2517
Max Act: 6.0642. Min Act: -0.1700
Data Index: 6787668 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2517. Min Range: -7.2517
Max Act: 6.0017. Min Act: -0.1700
Data Index: 8706131 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2517. Min Range: -7.2517
Max Act: 6.0330. Min Act: -0.1700
Data Index: 8576358 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2517. Min Range: -7.2517
Max Act: 5.9705. Min Act: -0.1700
Data Index: 5008510 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2517. Min Range: -7.2517
Max Act: 5.9392. Min Act: -0.1700
Data Index: 6773540 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2517. Min Range: -7.2517
Max Act: 5.8767. Min Act: -0.1700
Data Index: 6787666 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2517. Min Range: -7.2517
Max Act: 5.8455. Min Act: -0.1700
Data Index: 7626731 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2517. Min Range: -7.2517
Max Act: 5.8455. Min Act: -0.1700
Data Index: 7626729 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2517. Min Range: -7.2517
Max Act: 5.7830. Min Act: -0.1700
Data Index: 3927060 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2517. Min Range: -7.2517
Max Act: 5.7830. Min Act: -0.1700
Data Index: 5398964 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2517. Min Range: -7.2517
Max Act: 5.7830. Min Act: -0.1700
Data Index: 30388 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2517. Min Range: -7.2517
Max Act: 5.7517. Min Act: -0.1700
Data Index: 8055508 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2517. Min Range: -7.2517
Max Act: 5.7205. Min Act: -0.1700
Data Index: 5329194 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2517. Min Range: -7.2517
Max Act: 5.7205. Min Act: -0.1700
Data Index: 247151 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2517. Min Range: -7.2517
Max Act: 5.7205. Min Act: -0.1700
Data Index: 5398966 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19