Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2931 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0495. Min Range: -8.0495
Max Act: 8.0495. Min Act: -0.1700
Data Index: 6260421 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0495. Min Range: -8.0495
Max Act: 8.0495. Min Act: -0.1700
Data Index: 4568228 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0495. Min Range: -8.0495
Max Act: 8.0495. Min Act: -0.1700
Data Index: 5635225 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0495. Min Range: -8.0495
Max Act: 7.8620. Min Act: -0.1700
Data Index: 2183276 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0495. Min Range: -8.0495
Max Act: 7.8620. Min Act: -0.1700
Data Index: 108457 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0495. Min Range: -8.0495
Max Act: 7.7995. Min Act: -0.1700
Data Index: 7543621 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0495. Min Range: -8.0495
Max Act: 7.7995. Min Act: -0.1700
Data Index: 7853731 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0495. Min Range: -8.0495
Max Act: 7.7995. Min Act: -0.1700
Data Index: 3852930 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0495. Min Range: -8.0495
Max Act: 7.8620. Min Act: -0.1700
Data Index: 5979688 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0495. Min Range: -8.0495
Max Act: 7.7370. Min Act: -0.1700
Data Index: 4158951 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0495. Min Range: -8.0495
Max Act: 7.7058. Min Act: -0.1700
Data Index: 1602228 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0495. Min Range: -8.0495
Max Act: 7.7058. Min Act: -0.1700
Data Index: 8455173 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0495. Min Range: -8.0495
Max Act: 7.7058. Min Act: -0.1700
Data Index: 1048018 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0495. Min Range: -8.0495
Max Act: 7.6120. Min Act: -0.1700
Data Index: 5950505 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0495. Min Range: -8.0495
Max Act: 7.6433. Min Act: -0.1700
Data Index: 2865480 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0495. Min Range: -8.0495
Max Act: 7.5808. Min Act: -0.1700
Data Index: 3812660 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0495. Min Range: -8.0495
Max Act: 7.5808. Min Act: -0.1700
Data Index: 1277901 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0495. Min Range: -8.0495
Max Act: 7.5808. Min Act: -0.1700
Data Index: 2826832 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0495. Min Range: -8.0495
Max Act: 7.5495. Min Act: -0.1700
Data Index: 942473 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0495. Min Range: -8.0495
Max Act: 7.4870. Min Act: -0.1700
Data Index: 453640 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #19