Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3149 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.4798. Min Act: -0.1700
Data Index: 7933269 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.3861. Min Act: -0.1700
Data Index: 4217189 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.3861. Min Act: -0.1700
Data Index: 5067548 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.3861. Min Act: -0.1700
Data Index: 8614567 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.3236. Min Act: -0.1700
Data Index: 5619008 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.2923. Min Act: -0.1700
Data Index: 3737887 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.2611. Min Act: -0.1700
Data Index: 5663452 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.1986. Min Act: -0.1700
Data Index: 7090408 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.1361. Min Act: -0.1700
Data Index: 4139684 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.1361. Min Act: -0.1700
Data Index: 1156077 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.1048. Min Act: -0.1700
Data Index: 1869322 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.1361. Min Act: -0.1700
Data Index: 2493680 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.1048. Min Act: -0.1700
Data Index: 6372767 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.1048. Min Act: -0.1700
Data Index: 4243393 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.0736. Min Act: -0.1700
Data Index: 4370239 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.0736. Min Act: -0.1700
Data Index: 1728413 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.0736. Min Act: -0.1700
Data Index: 773269 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.0736. Min Act: -0.1700
Data Index: 7955365 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.0736. Min Act: -0.1700
Data Index: 7877944 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.0111. Min Act: -0.1700
Data Index: 5820589 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #19