Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 222 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7624. Min Range: -7.7624
Max Act: 7.7624. Min Act: -0.1700
Data Index: 4852211 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7624. Min Range: -7.7624
Max Act: 7.3249. Min Act: -0.1700
Data Index: 7196368 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7624. Min Range: -7.7624
Max Act: 6.9187. Min Act: -0.1700
Data Index: 8633038 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7624. Min Range: -7.7624
Max Act: 6.9187. Min Act: -0.1700
Data Index: 6292198 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7624. Min Range: -7.7624
Max Act: 6.7937. Min Act: -0.1700
Data Index: 6643405 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7624. Min Range: -7.7624
Max Act: 6.7937. Min Act: -0.1700
Data Index: 1028639 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7624. Min Range: -7.7624
Max Act: 6.6999. Min Act: -0.1700
Data Index: 6561116 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7624. Min Range: -7.7624
Max Act: 6.6687. Min Act: -0.1700
Data Index: 7811068 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7624. Min Range: -7.7624
Max Act: 6.6687. Min Act: -0.1700
Data Index: 8759863 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7624. Min Range: -7.7624
Max Act: 6.6374. Min Act: -0.1700
Data Index: 1513630 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7624. Min Range: -7.7624
Max Act: 6.6374. Min Act: -0.1700
Data Index: 6769336 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7624. Min Range: -7.7624
Max Act: 6.5437. Min Act: -0.1700
Data Index: 198156 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7624. Min Range: -7.7624
Max Act: 6.5124. Min Act: -0.1700
Data Index: 845866 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7624. Min Range: -7.7624
Max Act: 6.5437. Min Act: -0.1700
Data Index: 8205131 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7624. Min Range: -7.7624
Max Act: 6.4812. Min Act: -0.1700
Data Index: 7543516 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7624. Min Range: -7.7624
Max Act: 6.4499. Min Act: -0.1700
Data Index: 2241076 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7624. Min Range: -7.7624
Max Act: 6.4187. Min Act: -0.1700
Data Index: 5124638 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7624. Min Range: -7.7624
Max Act: 6.4187. Min Act: -0.1700
Data Index: 2585989 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7624. Min Range: -7.7624
Max Act: 6.4187. Min Act: -0.1700
Data Index: 8149035 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7624. Min Range: -7.7624
Max Act: 6.3874. Min Act: -0.1700
Data Index: 1775168 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #19