Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3686 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2635. Min Range: -5.2635
Max Act: 5.2635. Min Act: -0.1700
Data Index: 7418447 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2635. Min Range: -5.2635
Max Act: 5.2635. Min Act: -0.1700
Data Index: 3848371 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2635. Min Range: -5.2635
Max Act: 5.2323. Min Act: -0.1700
Data Index: 7694417 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2635. Min Range: -5.2635
Max Act: 5.2010. Min Act: -0.1700
Data Index: 2418535 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2635. Min Range: -5.2635
Max Act: 5.2010. Min Act: -0.1700
Data Index: 1149272 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2635. Min Range: -5.2635
Max Act: 5.2010. Min Act: -0.1700
Data Index: 7682444 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2635. Min Range: -5.2635
Max Act: 5.2010. Min Act: -0.1700
Data Index: 7196268 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2635. Min Range: -5.2635
Max Act: 5.1698. Min Act: -0.1700
Data Index: 5218960 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2635. Min Range: -5.2635
Max Act: 5.0760. Min Act: -0.1700
Data Index: 4449148 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2635. Min Range: -5.2635
Max Act: 5.0760. Min Act: -0.1700
Data Index: 738954 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2635. Min Range: -5.2635
Max Act: 5.0448. Min Act: -0.1700
Data Index: 5112499 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2635. Min Range: -5.2635
Max Act: 5.0135. Min Act: -0.1700
Data Index: 4067671 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2635. Min Range: -5.2635
Max Act: 5.0135. Min Act: -0.1700
Data Index: 1204720 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2635. Min Range: -5.2635
Max Act: 5.0135. Min Act: -0.1700
Data Index: 7693858 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2635. Min Range: -5.2635
Max Act: 4.9823. Min Act: -0.1700
Data Index: 6390919 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2635. Min Range: -5.2635
Max Act: 4.9823. Min Act: -0.1700
Data Index: 569567 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2635. Min Range: -5.2635
Max Act: 4.9823. Min Act: -0.1700
Data Index: 765518 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2635. Min Range: -5.2635
Max Act: 4.9510. Min Act: -0.1700
Data Index: 6032038 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2635. Min Range: -5.2635
Max Act: 4.9510. Min Act: -0.1700
Data Index: 3399005 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2635. Min Range: -5.2635
Max Act: 4.9823. Min Act: -0.1700
Data Index: 2521423 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19