Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4069 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.9375. Min Range: -10.9375
Max Act: 10.9375. Min Act: -0.1700
Data Index: 4029658 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9375. Min Range: -10.9375
Max Act: 10.5625. Min Act: -0.1700
Data Index: 700534 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9375. Min Range: -10.9375
Max Act: 10.3125. Min Act: -0.1700
Data Index: 7502774 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9375. Min Range: -10.9375
Max Act: 10.3750. Min Act: -0.1700
Data Index: 4039725 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9375. Min Range: -10.9375
Max Act: 10.2500. Min Act: -0.1700
Data Index: 3733018 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9375. Min Range: -10.9375
Max Act: 10.1250. Min Act: -0.1700
Data Index: 5037623 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9375. Min Range: -10.9375
Max Act: 10.0000. Min Act: -0.1700
Data Index: 6114160 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9375. Min Range: -10.9375
Max Act: 10.1250. Min Act: -0.1700
Data Index: 7531548 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9375. Min Range: -10.9375
Max Act: 10.0625. Min Act: -0.1700
Data Index: 4029683 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9375. Min Range: -10.9375
Max Act: 10.0000. Min Act: -0.1700
Data Index: 4029659 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9375. Min Range: -10.9375
Max Act: 10.0000. Min Act: -0.1700
Data Index: 4029677 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9375. Min Range: -10.9375
Max Act: 9.8750. Min Act: -0.1700
Data Index: 2028616 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9375. Min Range: -10.9375
Max Act: 9.7500. Min Act: -0.1700
Data Index: 5440421 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9375. Min Range: -10.9375
Max Act: 9.6875. Min Act: -0.1700
Data Index: 3217378 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9375. Min Range: -10.9375
Max Act: 9.6875. Min Act: -0.1700
Data Index: 4487045 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9375. Min Range: -10.9375
Max Act: 9.6875. Min Act: -0.1700
Data Index: 3647338 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9375. Min Range: -10.9375
Max Act: 9.6250. Min Act: -0.1700
Data Index: 2971626 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9375. Min Range: -10.9375
Max Act: 9.6250. Min Act: -0.1700
Data Index: 6602146 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9375. Min Range: -10.9375
Max Act: 9.6250. Min Act: -0.1700
Data Index: 2474257 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9375. Min Range: -10.9375
Max Act: 9.6250. Min Act: -0.1700
Data Index: 28624 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #19