Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5808 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6496. Min Range: -5.6496
Max Act: 5.6496. Min Act: -0.1700
Data Index: 4136789 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6496. Min Range: -5.6496
Max Act: 5.5558. Min Act: -0.1700
Data Index: 7165218 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6496. Min Range: -5.6496
Max Act: 5.5246. Min Act: -0.1700
Data Index: 4023962 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6496. Min Range: -5.6496
Max Act: 5.5246. Min Act: -0.1700
Data Index: 5315469 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6496. Min Range: -5.6496
Max Act: 5.4308. Min Act: -0.1700
Data Index: 1784221 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6496. Min Range: -5.6496
Max Act: 5.4308. Min Act: -0.1700
Data Index: 6023866 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6496. Min Range: -5.6496
Max Act: 5.3996. Min Act: -0.1700
Data Index: 8239570 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6496. Min Range: -5.6496
Max Act: 5.3996. Min Act: -0.1700
Data Index: 2349809 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6496. Min Range: -5.6496
Max Act: 5.3996. Min Act: -0.1700
Data Index: 3651052 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6496. Min Range: -5.6496
Max Act: 5.3683. Min Act: -0.1700
Data Index: 1590996 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6496. Min Range: -5.6496
Max Act: 5.3058. Min Act: -0.1700
Data Index: 2724331 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6496. Min Range: -5.6496
Max Act: 5.2746. Min Act: -0.1700
Data Index: 1590995 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6496. Min Range: -5.6496
Max Act: 5.2433. Min Act: -0.1700
Data Index: 8566780 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6496. Min Range: -5.6496
Max Act: 5.2746. Min Act: -0.1700
Data Index: 2727618 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6496. Min Range: -5.6496
Max Act: 5.2433. Min Act: -0.1700
Data Index: 329667 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6496. Min Range: -5.6496
Max Act: 5.2746. Min Act: -0.1700
Data Index: 797941 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6496. Min Range: -5.6496
Max Act: 5.2433. Min Act: -0.1700
Data Index: 644614 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6496. Min Range: -5.6496
Max Act: 5.2433. Min Act: -0.1700
Data Index: 2349808 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6496. Min Range: -5.6496
Max Act: 5.2121. Min Act: -0.1700
Data Index: 7463038 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6496. Min Range: -5.6496
Max Act: 5.2433. Min Act: -0.1700
Data Index: 3643107 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #19