Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3564 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0566. Min Range: -6.0566
Max Act: 6.0566. Min Act: -0.1700
Data Index: 1229372 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0566. Min Range: -6.0566
Max Act: 6.0254. Min Act: -0.1700
Data Index: 6039356 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0566. Min Range: -6.0566
Max Act: 5.9629. Min Act: -0.1700
Data Index: 7853946 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0566. Min Range: -6.0566
Max Act: 5.9316. Min Act: -0.1700
Data Index: 1469874 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0566. Min Range: -6.0566
Max Act: 5.9316. Min Act: -0.1700
Data Index: 599980 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0566. Min Range: -6.0566
Max Act: 5.9316. Min Act: -0.1700
Data Index: 7490040 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0566. Min Range: -6.0566
Max Act: 5.9316. Min Act: -0.1700
Data Index: 1029412 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0566. Min Range: -6.0566
Max Act: 5.9004. Min Act: -0.1700
Data Index: 4629391 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0566. Min Range: -6.0566
Max Act: 5.9004. Min Act: -0.1700
Data Index: 3733466 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0566. Min Range: -6.0566
Max Act: 5.9004. Min Act: -0.1700
Data Index: 7860165 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0566. Min Range: -6.0566
Max Act: 5.9004. Min Act: -0.1700
Data Index: 7971845 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0566. Min Range: -6.0566
Max Act: 5.9004. Min Act: -0.1700
Data Index: 6703924 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0566. Min Range: -6.0566
Max Act: 5.8691. Min Act: -0.1700
Data Index: 3332581 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0566. Min Range: -6.0566
Max Act: 5.8691. Min Act: -0.1700
Data Index: 7974296 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0566. Min Range: -6.0566
Max Act: 5.8691. Min Act: -0.1700
Data Index: 7655340 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0566. Min Range: -6.0566
Max Act: 5.8691. Min Act: -0.1700
Data Index: 2120302 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0566. Min Range: -6.0566
Max Act: 5.8691. Min Act: -0.1700
Data Index: 1167493 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0566. Min Range: -6.0566
Max Act: 5.8379. Min Act: -0.1700
Data Index: 3634675 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0566. Min Range: -6.0566
Max Act: 5.8379. Min Act: -0.1700
Data Index: 7354277 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0566. Min Range: -6.0566
Max Act: 5.8379. Min Act: -0.1698
Data Index: 7357299 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #19