Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4722 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7634. Min Range: -5.7634
Max Act: 5.7634. Min Act: -0.1700
Data Index: 6413390 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7634. Min Range: -5.7634
Max Act: 5.7321. Min Act: -0.1700
Data Index: 4591587 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7634. Min Range: -5.7634
Max Act: 5.7321. Min Act: -0.1700
Data Index: 4158728 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7634. Min Range: -5.7634
Max Act: 5.7009. Min Act: -0.1700
Data Index: 5440225 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7634. Min Range: -5.7634
Max Act: 5.6696. Min Act: -0.1700
Data Index: 6977385 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7634. Min Range: -5.7634
Max Act: 5.6696. Min Act: -0.1700
Data Index: 5600249 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7634. Min Range: -5.7634
Max Act: 5.6384. Min Act: -0.1700
Data Index: 689475 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7634. Min Range: -5.7634
Max Act: 5.6071. Min Act: -0.1700
Data Index: 1083053 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7634. Min Range: -5.7634
Max Act: 5.5759. Min Act: -0.1700
Data Index: 6299010 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7634. Min Range: -5.7634
Max Act: 5.5759. Min Act: -0.1700
Data Index: 5708602 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7634. Min Range: -5.7634
Max Act: 5.5759. Min Act: -0.1700
Data Index: 6737624 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7634. Min Range: -5.7634
Max Act: 5.5446. Min Act: -0.1700
Data Index: 3057414 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7634. Min Range: -5.7634
Max Act: 5.5446. Min Act: -0.1700
Data Index: 7595854 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7634. Min Range: -5.7634
Max Act: 5.5446. Min Act: -0.1700
Data Index: 6413394 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7634. Min Range: -5.7634
Max Act: 5.5446. Min Act: -0.1700
Data Index: 1609978 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7634. Min Range: -5.7634
Max Act: 5.5446. Min Act: -0.1700
Data Index: 1952913 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7634. Min Range: -5.7634
Max Act: 5.5446. Min Act: -0.1700
Data Index: 1035409 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7634. Min Range: -5.7634
Max Act: 5.5134. Min Act: -0.1700
Data Index: 3366027 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7634. Min Range: -5.7634
Max Act: 5.5134. Min Act: -0.1700
Data Index: 3867354 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7634. Min Range: -5.7634
Max Act: 5.4821. Min Act: -0.1700
Data Index: 3591527 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19