Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1626 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0831. Min Range: -5.0831
Max Act: 5.0831. Min Act: -0.1700
Data Index: 191412 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0831. Min Range: -5.0831
Max Act: 5.0831. Min Act: -0.1700
Data Index: 3560481 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0831. Min Range: -5.0831
Max Act: 4.9893. Min Act: -0.1700
Data Index: 6067928 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0831. Min Range: -5.0831
Max Act: 4.9268. Min Act: -0.1700
Data Index: 6350212 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0831. Min Range: -5.0831
Max Act: 4.9268. Min Act: -0.1700
Data Index: 5868371 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0831. Min Range: -5.0831
Max Act: 4.8643. Min Act: -0.1700
Data Index: 2069218 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0831. Min Range: -5.0831
Max Act: 4.8956. Min Act: -0.1700
Data Index: 4239706 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0831. Min Range: -5.0831
Max Act: 4.8331. Min Act: -0.1700
Data Index: 816299 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0831. Min Range: -5.0831
Max Act: 4.8331. Min Act: -0.1700
Data Index: 8225784 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0831. Min Range: -5.0831
Max Act: 4.8331. Min Act: -0.1700
Data Index: 652770 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0831. Min Range: -5.0831
Max Act: 4.8331. Min Act: -0.1700
Data Index: 6888593 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0831. Min Range: -5.0831
Max Act: 4.8018. Min Act: -0.1700
Data Index: 108697 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0831. Min Range: -5.0831
Max Act: 4.8018. Min Act: -0.1700
Data Index: 4263422 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0831. Min Range: -5.0831
Max Act: 4.7706. Min Act: -0.1700
Data Index: 5504204 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0831. Min Range: -5.0831
Max Act: 4.8018. Min Act: -0.1700
Data Index: 5189882 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0831. Min Range: -5.0831
Max Act: 4.8018. Min Act: -0.1700
Data Index: 2658778 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0831. Min Range: -5.0831
Max Act: 4.7706. Min Act: -0.1700
Data Index: 373156 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0831. Min Range: -5.0831
Max Act: 4.7706. Min Act: -0.1700
Data Index: 6557719 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0831. Min Range: -5.0831
Max Act: 4.7706. Min Act: -0.1700
Data Index: 5761620 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0831. Min Range: -5.0831
Max Act: 4.7706. Min Act: -0.1700
Data Index: 3989808 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #19