Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4095 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3651. Min Range: -5.3651
Max Act: 5.3651. Min Act: -0.1700
Data Index: 4981838 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3651. Min Range: -5.3651
Max Act: 5.1776. Min Act: -0.1700
Data Index: 8332627 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3651. Min Range: -5.3651
Max Act: 5.1151. Min Act: -0.1699
Data Index: 3981378 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3651. Min Range: -5.3651
Max Act: 5.1151. Min Act: -0.1700
Data Index: 4081510 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3651. Min Range: -5.3651
Max Act: 5.1151. Min Act: -0.1700
Data Index: 2855749 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3651. Min Range: -5.3651
Max Act: 5.0838. Min Act: -0.1700
Data Index: 3511521 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3651. Min Range: -5.3651
Max Act: 5.0838. Min Act: -0.1700
Data Index: 3780931 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3651. Min Range: -5.3651
Max Act: 5.0838. Min Act: -0.1700
Data Index: 7603891 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3651. Min Range: -5.3651
Max Act: 5.0838. Min Act: -0.1700
Data Index: 647572 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3651. Min Range: -5.3651
Max Act: 5.0526. Min Act: -0.1700
Data Index: 2705100 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3651. Min Range: -5.3651
Max Act: 5.0526. Min Act: -0.1700
Data Index: 3822214 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3651. Min Range: -5.3651
Max Act: 5.0213. Min Act: -0.1700
Data Index: 1927062 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3651. Min Range: -5.3651
Max Act: 5.0213. Min Act: -0.1700
Data Index: 8676904 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3651. Min Range: -5.3651
Max Act: 4.9901. Min Act: -0.1700
Data Index: 5469715 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3651. Min Range: -5.3651
Max Act: 4.9901. Min Act: -0.1698
Data Index: 768380 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3651. Min Range: -5.3651
Max Act: 4.9901. Min Act: -0.1700
Data Index: 7185954 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3651. Min Range: -5.3651
Max Act: 4.9588. Min Act: -0.1700
Data Index: 6177054 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3651. Min Range: -5.3651
Max Act: 4.9588. Min Act: -0.1700
Data Index: 6328453 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3651. Min Range: -5.3651
Max Act: 4.9588. Min Act: -0.1700
Data Index: 1380699 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3651. Min Range: -5.3651
Max Act: 4.9276. Min Act: -0.1700
Data Index: 8060331 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19