Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0079. Min Range: -4.0079
Max Act: 4.0079. Min Act: -0.1700
Data Index: 6751674 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0079. Min Range: -4.0079
Max Act: 3.9766. Min Act: -0.1700
Data Index: 1493347 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0079. Min Range: -4.0079
Max Act: 3.9766. Min Act: -0.1700
Data Index: 6002885 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0079. Min Range: -4.0079
Max Act: 3.9453. Min Act: -0.1698
Data Index: 5474812 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0079. Min Range: -4.0079
Max Act: 3.9141. Min Act: -0.1700
Data Index: 5474811 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0079. Min Range: -4.0079
Max Act: 3.9141. Min Act: -0.1700
Data Index: 6002884 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0079. Min Range: -4.0079
Max Act: 3.8828. Min Act: -0.1697
Data Index: 5303647 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0079. Min Range: -4.0079
Max Act: 3.8515. Min Act: -0.1700
Data Index: 7605313 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0079. Min Range: -4.0079
Max Act: 3.8515. Min Act: -0.1700
Data Index: 5758016 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0079. Min Range: -4.0079
Max Act: 3.8203. Min Act: -0.1700
Data Index: 1246509 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0079. Min Range: -4.0079
Max Act: 3.8203. Min Act: -0.1700
Data Index: 402866 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0079. Min Range: -4.0079
Max Act: 3.7890. Min Act: -0.1700
Data Index: 5995816 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0079. Min Range: -4.0079
Max Act: 3.8203. Min Act: -0.1700
Data Index: 4995078 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0079. Min Range: -4.0079
Max Act: 3.8203. Min Act: -0.1700
Data Index: 2379076 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0079. Min Range: -4.0079
Max Act: 3.8203. Min Act: -0.1700
Data Index: 6794232 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0079. Min Range: -4.0079
Max Act: 3.8203. Min Act: -0.1700
Data Index: 6143068 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0079. Min Range: -4.0079
Max Act: 3.8203. Min Act: -0.1700
Data Index: 974088 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0079. Min Range: -4.0079
Max Act: 3.7890. Min Act: -0.1700
Data Index: 4947146 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0079. Min Range: -4.0079
Max Act: 3.7577. Min Act: -0.1700
Data Index: 449013 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0079. Min Range: -4.0079
Max Act: 3.7890. Min Act: -0.1700
Data Index: 1840837 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #19