Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3480 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2984. Min Range: -6.2984
Max Act: 6.2984. Min Act: -0.1700
Data Index: 8106934 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2984. Min Range: -6.2984
Max Act: 6.0797. Min Act: -0.1699
Data Index: 6324309 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2984. Min Range: -6.2984
Max Act: 6.0797. Min Act: -0.1700
Data Index: 75410 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2984. Min Range: -6.2984
Max Act: 6.0484. Min Act: -0.1700
Data Index: 8161547 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2984. Min Range: -6.2984
Max Act: 5.9859. Min Act: -0.1700
Data Index: 7126200 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2984. Min Range: -6.2984
Max Act: 5.9234. Min Act: -0.1700
Data Index: 192655 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2984. Min Range: -6.2984
Max Act: 5.9547. Min Act: -0.1700
Data Index: 4583812 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2984. Min Range: -6.2984
Max Act: 5.9547. Min Act: -0.1700
Data Index: 3704262 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2984. Min Range: -6.2984
Max Act: 5.9234. Min Act: -0.1700
Data Index: 321745 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2984. Min Range: -6.2984
Max Act: 5.8922. Min Act: -0.1700
Data Index: 3306802 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2984. Min Range: -6.2984
Max Act: 5.8922. Min Act: -0.1700
Data Index: 3685135 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2984. Min Range: -6.2984
Max Act: 5.8922. Min Act: -0.1700
Data Index: 536193 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2984. Min Range: -6.2984
Max Act: 5.8922. Min Act: -0.1700
Data Index: 8416057 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2984. Min Range: -6.2984
Max Act: 5.8609. Min Act: -0.1700
Data Index: 45557 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2984. Min Range: -6.2984
Max Act: 5.8609. Min Act: -0.1700
Data Index: 2658398 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2984. Min Range: -6.2984
Max Act: 5.8297. Min Act: -0.1700
Data Index: 484627 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2984. Min Range: -6.2984
Max Act: 5.8297. Min Act: -0.1700
Data Index: 4395901 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2984. Min Range: -6.2984
Max Act: 5.8297. Min Act: -0.1700
Data Index: 8316731 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2984. Min Range: -6.2984
Max Act: 5.8297. Min Act: -0.1700
Data Index: 238673 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2984. Min Range: -6.2984
Max Act: 5.7984. Min Act: -0.1700
Data Index: 150772 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19