Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3451 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7110. Min Range: -5.7110
Max Act: 5.7110. Min Act: -0.1700
Data Index: 8201785 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7110. Min Range: -5.7110
Max Act: 5.6798. Min Act: -0.1700
Data Index: 1582552 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7110. Min Range: -5.7110
Max Act: 5.6798. Min Act: -0.1700
Data Index: 2920454 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7110. Min Range: -5.7110
Max Act: 5.6173. Min Act: -0.1700
Data Index: 8544551 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7110. Min Range: -5.7110
Max Act: 5.5860. Min Act: -0.1700
Data Index: 888470 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7110. Min Range: -5.7110
Max Act: 5.4610. Min Act: -0.1700
Data Index: 1555032 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7110. Min Range: -5.7110
Max Act: 5.4610. Min Act: -0.1700
Data Index: 4183851 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7110. Min Range: -5.7110
Max Act: 5.3985. Min Act: -0.1700
Data Index: 7977 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7110. Min Range: -5.7110
Max Act: 5.4298. Min Act: -0.1700
Data Index: 4552038 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7110. Min Range: -5.7110
Max Act: 5.3985. Min Act: -0.1700
Data Index: 3856145 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7110. Min Range: -5.7110
Max Act: 5.3673. Min Act: -0.1700
Data Index: 5606915 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7110. Min Range: -5.7110
Max Act: 5.3360. Min Act: -0.1700
Data Index: 8773199 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7110. Min Range: -5.7110
Max Act: 5.3360. Min Act: -0.1700
Data Index: 7631319 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7110. Min Range: -5.7110
Max Act: 5.3360. Min Act: -0.1700
Data Index: 8236386 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7110. Min Range: -5.7110
Max Act: 5.3360. Min Act: -0.1700
Data Index: 2017604 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7110. Min Range: -5.7110
Max Act: 5.3048. Min Act: -0.1700
Data Index: 7005318 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7110. Min Range: -5.7110
Max Act: 5.3048. Min Act: -0.1700
Data Index: 3181450 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7110. Min Range: -5.7110
Max Act: 5.3048. Min Act: -0.1700
Data Index: 2301995 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7110. Min Range: -5.7110
Max Act: 5.3048. Min Act: -0.1700
Data Index: 8355659 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7110. Min Range: -5.7110
Max Act: 5.2735. Min Act: -0.1700
Data Index: 7546641 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #19