Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2294 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0150. Min Range: -3.0150
Max Act: 3.0150. Min Act: -0.1700
Data Index: 5058361 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0150. Min Range: -3.0150
Max Act: 2.9992. Min Act: -0.1700
Data Index: 1483205 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0150. Min Range: -3.0150
Max Act: 3.0150. Min Act: -0.1700
Data Index: 6794201 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0150. Min Range: -3.0150
Max Act: 2.9992. Min Act: -0.1700
Data Index: 763350 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0150. Min Range: -3.0150
Max Act: 2.9834. Min Act: -0.1700
Data Index: 8227663 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0150. Min Range: -3.0150
Max Act: 2.9675. Min Act: -0.1700
Data Index: 483797 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0150. Min Range: -3.0150
Max Act: 2.9675. Min Act: -0.1700
Data Index: 6930907 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0150. Min Range: -3.0150
Max Act: 2.9517. Min Act: -0.1700
Data Index: 3179667 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0150. Min Range: -3.0150
Max Act: 2.9675. Min Act: -0.1700
Data Index: 2315355 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0150. Min Range: -3.0150
Max Act: 2.9517. Min Act: -0.1700
Data Index: 3712831 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0150. Min Range: -3.0150
Max Act: 2.9359. Min Act: -0.1700
Data Index: 6235853 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0150. Min Range: -3.0150
Max Act: 2.9359. Min Act: -0.1700
Data Index: 6933213 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0150. Min Range: -3.0150
Max Act: 2.9359. Min Act: -0.1700
Data Index: 2475967 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0150. Min Range: -3.0150
Max Act: 2.9359. Min Act: -0.1700
Data Index: 6928421 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0150. Min Range: -3.0150
Max Act: 2.9359. Min Act: -0.1700
Data Index: 1181697 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0150. Min Range: -3.0150
Max Act: 2.9359. Min Act: -0.1700
Data Index: 5099071 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0150. Min Range: -3.0150
Max Act: 2.9359. Min Act: -0.1700
Data Index: 1511976 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0150. Min Range: -3.0150
Max Act: 2.9359. Min Act: -0.1700
Data Index: 4623715 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0150. Min Range: -3.0150
Max Act: 2.9359. Min Act: -0.1700
Data Index: 4144368 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0150. Min Range: -3.0150
Max Act: 2.9359. Min Act: -0.1700
Data Index: 4786416 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19