Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1063 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3271. Min Range: -7.3271
Max Act: 7.3271. Min Act: -0.1700
Data Index: 8586581 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3271. Min Range: -7.3271
Max Act: 7.0771. Min Act: -0.1700
Data Index: 4063700 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3271. Min Range: -7.3271
Max Act: 7.0771. Min Act: -0.1700
Data Index: 2180584 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3271. Min Range: -7.3271
Max Act: 7.0146. Min Act: -0.1700
Data Index: 5038426 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3271. Min Range: -7.3271
Max Act: 7.0458. Min Act: -0.1700
Data Index: 979997 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3271. Min Range: -7.3271
Max Act: 6.9833. Min Act: -0.1700
Data Index: 2180582 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3271. Min Range: -7.3271
Max Act: 6.9833. Min Act: -0.1700
Data Index: 4668206 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3271. Min Range: -7.3271
Max Act: 6.8583. Min Act: -0.1700
Data Index: 968376 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3271. Min Range: -7.3271
Max Act: 6.8583. Min Act: -0.1700
Data Index: 4121591 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3271. Min Range: -7.3271
Max Act: 6.8271. Min Act: -0.1700
Data Index: 4328257 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3271. Min Range: -7.3271
Max Act: 6.8271. Min Act: -0.1700
Data Index: 5722435 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3271. Min Range: -7.3271
Max Act: 6.7646. Min Act: -0.1700
Data Index: 8716431 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3271. Min Range: -7.3271
Max Act: 6.7646. Min Act: -0.1700
Data Index: 4405699 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3271. Min Range: -7.3271
Max Act: 6.7958. Min Act: -0.1700
Data Index: 4942354 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3271. Min Range: -7.3271
Max Act: 6.7958. Min Act: -0.1700
Data Index: 5411021 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3271. Min Range: -7.3271
Max Act: 6.7333. Min Act: -0.1700
Data Index: 4098864 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3271. Min Range: -7.3271
Max Act: 6.7333. Min Act: -0.1700
Data Index: 1631443 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3271. Min Range: -7.3271
Max Act: 6.7333. Min Act: -0.1700
Data Index: 1660621 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3271. Min Range: -7.3271
Max Act: 6.7021. Min Act: -0.1700
Data Index: 1359793 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3271. Min Range: -7.3271
Max Act: 6.6708. Min Act: -0.1700
Data Index: 4212357 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #19