Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3888 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9642. Min Range: -6.9642
Max Act: 6.9642. Min Act: -0.1700
Data Index: 4710160 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9642. Min Range: -6.9642
Max Act: 6.9329. Min Act: -0.1700
Data Index: 1427772 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9642. Min Range: -6.9642
Max Act: 6.9642. Min Act: -0.1700
Data Index: 7562487 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9642. Min Range: -6.9642
Max Act: 6.9017. Min Act: -0.1700
Data Index: 5045697 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9642. Min Range: -6.9642
Max Act: 6.8704. Min Act: -0.1700
Data Index: 3115353 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9642. Min Range: -6.9642
Max Act: 6.8392. Min Act: -0.1700
Data Index: 5827059 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9642. Min Range: -6.9642
Max Act: 6.8392. Min Act: -0.1700
Data Index: 4558191 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9642. Min Range: -6.9642
Max Act: 6.8392. Min Act: -0.1700
Data Index: 3324472 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9642. Min Range: -6.9642
Max Act: 6.8079. Min Act: -0.1700
Data Index: 7302697 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9642. Min Range: -6.9642
Max Act: 6.7454. Min Act: -0.1700
Data Index: 8012987 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9642. Min Range: -6.9642
Max Act: 6.7142. Min Act: -0.1700
Data Index: 3510643 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9642. Min Range: -6.9642
Max Act: 6.7454. Min Act: -0.1700
Data Index: 6505587 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9642. Min Range: -6.9642
Max Act: 6.6829. Min Act: -0.1700
Data Index: 5959806 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9642. Min Range: -6.9642
Max Act: 6.6829. Min Act: -0.1700
Data Index: 4412491 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9642. Min Range: -6.9642
Max Act: 6.7142. Min Act: -0.1700
Data Index: 751849 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9642. Min Range: -6.9642
Max Act: 6.6517. Min Act: -0.1700
Data Index: 8539093 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9642. Min Range: -6.9642
Max Act: 6.6517. Min Act: -0.1700
Data Index: 8768497 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9642. Min Range: -6.9642
Max Act: 6.6204. Min Act: -0.1700
Data Index: 8537457 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9642. Min Range: -6.9642
Max Act: 6.6204. Min Act: -0.1700
Data Index: 6448242 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9642. Min Range: -6.9642
Max Act: 6.5892. Min Act: -0.1700
Data Index: 1532279 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19