Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1094 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5903. Min Range: -6.5903
Max Act: 6.5903. Min Act: -0.1700
Data Index: 3431563 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5903. Min Range: -6.5903
Max Act: 5.9965. Min Act: -0.1700
Data Index: 4742721 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5903. Min Range: -6.5903
Max Act: 5.9653. Min Act: -0.1700
Data Index: 1544571 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5903. Min Range: -6.5903
Max Act: 5.9028. Min Act: -0.1700
Data Index: 1353780 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5903. Min Range: -6.5903
Max Act: 5.8715. Min Act: -0.1700
Data Index: 4088990 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5903. Min Range: -6.5903
Max Act: 5.8403. Min Act: -0.1700
Data Index: 6549506 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5903. Min Range: -6.5903
Max Act: 5.8403. Min Act: -0.1700
Data Index: 8512421 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5903. Min Range: -6.5903
Max Act: 5.8403. Min Act: -0.1700
Data Index: 7623648 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5903. Min Range: -6.5903
Max Act: 5.7778. Min Act: -0.1700
Data Index: 3185593 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5903. Min Range: -6.5903
Max Act: 5.7778. Min Act: -0.1700
Data Index: 3856573 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5903. Min Range: -6.5903
Max Act: 5.7465. Min Act: -0.1700
Data Index: 7076818 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5903. Min Range: -6.5903
Max Act: 5.7153. Min Act: -0.1700
Data Index: 170528 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5903. Min Range: -6.5903
Max Act: 5.7153. Min Act: -0.1700
Data Index: 3552105 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5903. Min Range: -6.5903
Max Act: 5.6840. Min Act: -0.1700
Data Index: 2324497 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5903. Min Range: -6.5903
Max Act: 5.7153. Min Act: -0.1700
Data Index: 7890017 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5903. Min Range: -6.5903
Max Act: 5.7465. Min Act: -0.1700
Data Index: 4784652 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5903. Min Range: -6.5903
Max Act: 5.6840. Min Act: -0.1700
Data Index: 6195006 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5903. Min Range: -6.5903
Max Act: 5.6840. Min Act: -0.1700
Data Index: 1168873 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5903. Min Range: -6.5903
Max Act: 5.6840. Min Act: -0.1700
Data Index: 4914177 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5903. Min Range: -6.5903
Max Act: 5.6528. Min Act: -0.1700
Data Index: 6495813 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #19