Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3514 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2101. Min Range: -5.2101
Max Act: 5.2101. Min Act: -0.1700
Data Index: 4172273 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2101. Min Range: -5.2101
Max Act: 5.1788. Min Act: -0.1700
Data Index: 674140 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2101. Min Range: -5.2101
Max Act: 5.1476. Min Act: -0.1700
Data Index: 7879083 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2101. Min Range: -5.2101
Max Act: 5.1163. Min Act: -0.1700
Data Index: 7879090 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2101. Min Range: -5.2101
Max Act: 5.0538. Min Act: -0.1700
Data Index: 4875840 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2101. Min Range: -5.2101
Max Act: 5.0226. Min Act: -0.1700
Data Index: 7782054 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2101. Min Range: -5.2101
Max Act: 5.0226. Min Act: -0.1700
Data Index: 5052200 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2101. Min Range: -5.2101
Max Act: 5.0226. Min Act: -0.1700
Data Index: 7643086 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2101. Min Range: -5.2101
Max Act: 4.9601. Min Act: -0.1700
Data Index: 8459695 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2101. Min Range: -5.2101
Max Act: 4.9601. Min Act: -0.1700
Data Index: 6728613 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2101. Min Range: -5.2101
Max Act: 4.9288. Min Act: -0.1700
Data Index: 7879087 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2101. Min Range: -5.2101
Max Act: 4.9288. Min Act: -0.1700
Data Index: 681489 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2101. Min Range: -5.2101
Max Act: 4.9288. Min Act: -0.1700
Data Index: 5592678 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2101. Min Range: -5.2101
Max Act: 4.8976. Min Act: -0.1700
Data Index: 2675634 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2101. Min Range: -5.2101
Max Act: 4.8976. Min Act: -0.1700
Data Index: 6728615 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2101. Min Range: -5.2101
Max Act: 4.8976. Min Act: -0.1700
Data Index: 3135038 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2101. Min Range: -5.2101
Max Act: 4.8976. Min Act: -0.1700
Data Index: 1423625 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2101. Min Range: -5.2101
Max Act: 4.8976. Min Act: -0.1700
Data Index: 8269666 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2101. Min Range: -5.2101
Max Act: 4.9288. Min Act: -0.1700
Data Index: 8500675 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2101. Min Range: -5.2101
Max Act: 4.8663. Min Act: -0.1700
Data Index: 5274808 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #19