Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4006 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1441. Min Range: -4.1441
Max Act: 4.1441. Min Act: -0.1700
Data Index: 2645714 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1441. Min Range: -4.1441
Max Act: 4.1129. Min Act: -0.1700
Data Index: 3059456 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1441. Min Range: -4.1441
Max Act: 4.0816. Min Act: -0.1700
Data Index: 6932997 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1441. Min Range: -4.1441
Max Act: 4.0816. Min Act: -0.1700
Data Index: 8737727 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1441. Min Range: -4.1441
Max Act: 4.0504. Min Act: -0.1700
Data Index: 5955066 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1441. Min Range: -4.1441
Max Act: 4.0504. Min Act: -0.1700
Data Index: 1728858 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1441. Min Range: -4.1441
Max Act: 4.0191. Min Act: -0.1700
Data Index: 1478758 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1441. Min Range: -4.1441
Max Act: 4.0504. Min Act: -0.1700
Data Index: 1700386 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1441. Min Range: -4.1441
Max Act: 4.0504. Min Act: -0.1700
Data Index: 3512734 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1441. Min Range: -4.1441
Max Act: 4.0191. Min Act: -0.1700
Data Index: 1329779 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1441. Min Range: -4.1441
Max Act: 3.9879. Min Act: -0.1700
Data Index: 4918176 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1441. Min Range: -4.1441
Max Act: 4.0191. Min Act: -0.1700
Data Index: 2543184 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1441. Min Range: -4.1441
Max Act: 4.0191. Min Act: -0.1700
Data Index: 1022668 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1441. Min Range: -4.1441
Max Act: 3.9879. Min Act: -0.1700
Data Index: 2849051 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1441. Min Range: -4.1441
Max Act: 3.9879. Min Act: -0.1700
Data Index: 4894059 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1441. Min Range: -4.1441
Max Act: 3.9566. Min Act: -0.1700
Data Index: 3279349 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1441. Min Range: -4.1441
Max Act: 3.9879. Min Act: -0.1700
Data Index: 1279448 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1441. Min Range: -4.1441
Max Act: 3.8941. Min Act: -0.1700
Data Index: 3695862 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1441. Min Range: -4.1441
Max Act: 3.9253. Min Act: -0.1700
Data Index: 676677 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1441. Min Range: -4.1441
Max Act: 3.9253. Min Act: -0.1700
Data Index: 4739207 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19