Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3099 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9547. Min Range: -3.9547
Max Act: 3.9547. Min Act: -0.1700
Data Index: 8324907 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9547. Min Range: -3.9547
Max Act: 3.9234. Min Act: -0.1700
Data Index: 3010377 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9547. Min Range: -3.9547
Max Act: 3.8140. Min Act: -0.1700
Data Index: 5359754 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9547. Min Range: -3.9547
Max Act: 3.7827. Min Act: -0.1700
Data Index: 5085873 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9547. Min Range: -3.9547
Max Act: 3.7358. Min Act: -0.1700
Data Index: 6175904 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9547. Min Range: -3.9547
Max Act: 3.7202. Min Act: -0.1700
Data Index: 6986699 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9547. Min Range: -3.9547
Max Act: 3.6889. Min Act: -0.1700
Data Index: 8589822 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9547. Min Range: -3.9547
Max Act: 3.7045. Min Act: -0.1700
Data Index: 245545 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9547. Min Range: -3.9547
Max Act: 3.6889. Min Act: -0.1700
Data Index: 8184651 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9547. Min Range: -3.9547
Max Act: 3.6732. Min Act: -0.1700
Data Index: 7267590 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9547. Min Range: -3.9547
Max Act: 3.6889. Min Act: -0.1700
Data Index: 7445624 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9547. Min Range: -3.9547
Max Act: 3.7045. Min Act: -0.1700
Data Index: 7928620 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9547. Min Range: -3.9547
Max Act: 3.6576. Min Act: -0.1700
Data Index: 5037764 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9547. Min Range: -3.9547
Max Act: 3.6732. Min Act: -0.1700
Data Index: 6072621 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9547. Min Range: -3.9547
Max Act: 3.6732. Min Act: -0.1700
Data Index: 229911 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9547. Min Range: -3.9547
Max Act: 3.6576. Min Act: -0.1700
Data Index: 5682407 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9547. Min Range: -3.9547
Max Act: 3.6576. Min Act: -0.1700
Data Index: 6258781 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9547. Min Range: -3.9547
Max Act: 3.6419. Min Act: -0.1700
Data Index: 5920523 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9547. Min Range: -3.9547
Max Act: 3.6576. Min Act: -0.1700
Data Index: 7171321 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9547. Min Range: -3.9547
Max Act: 3.6419. Min Act: -0.1700
Data Index: 3051319 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #19