Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5834 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4107. Min Range: -5.4107
Max Act: 5.4107. Min Act: -0.1700
Data Index: 6461487 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4107. Min Range: -5.4107
Max Act: 5.2232. Min Act: -0.1700
Data Index: 4774903 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4107. Min Range: -5.4107
Max Act: 5.1607. Min Act: -0.1700
Data Index: 5382521 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4107. Min Range: -5.4107
Max Act: 5.1607. Min Act: -0.1700
Data Index: 414723 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4107. Min Range: -5.4107
Max Act: 5.0670. Min Act: -0.1700
Data Index: 6546362 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4107. Min Range: -5.4107
Max Act: 5.0670. Min Act: -0.1700
Data Index: 3780661 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4107. Min Range: -5.4107
Max Act: 5.0357. Min Act: -0.1700
Data Index: 6709596 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4107. Min Range: -5.4107
Max Act: 5.0045. Min Act: -0.1700
Data Index: 1202389 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4107. Min Range: -5.4107
Max Act: 5.0357. Min Act: -0.1700
Data Index: 1881453 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4107. Min Range: -5.4107
Max Act: 5.0045. Min Act: -0.1700
Data Index: 5704158 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4107. Min Range: -5.4107
Max Act: 4.9732. Min Act: -0.1700
Data Index: 6750836 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4107. Min Range: -5.4107
Max Act: 5.0045. Min Act: -0.1700
Data Index: 1918443 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4107. Min Range: -5.4107
Max Act: 4.9732. Min Act: -0.1700
Data Index: 7914787 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4107. Min Range: -5.4107
Max Act: 4.9732. Min Act: -0.1700
Data Index: 2187146 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4107. Min Range: -5.4107
Max Act: 4.9732. Min Act: -0.1700
Data Index: 7746246 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4107. Min Range: -5.4107
Max Act: 4.9732. Min Act: -0.1700
Data Index: 6709722 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4107. Min Range: -5.4107
Max Act: 4.9732. Min Act: -0.1700
Data Index: 1524163 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4107. Min Range: -5.4107
Max Act: 4.9420. Min Act: -0.1700
Data Index: 2132696 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4107. Min Range: -5.4107
Max Act: 4.9420. Min Act: -0.1700
Data Index: 1629332 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4107. Min Range: -5.4107
Max Act: 4.9732. Min Act: -0.1700
Data Index: 263733 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #19