Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3031 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8805. Min Range: -6.8805
Max Act: 6.8805. Min Act: -0.1700
Data Index: 475048 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8805. Min Range: -6.8805
Max Act: 6.8180. Min Act: -0.1700
Data Index: 2719843 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8805. Min Range: -6.8805
Max Act: 6.7868. Min Act: -0.1700
Data Index: 8460030 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8805. Min Range: -6.8805
Max Act: 6.6305. Min Act: -0.1700
Data Index: 3126557 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8805. Min Range: -6.8805
Max Act: 6.6305. Min Act: -0.1700
Data Index: 6406760 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8805. Min Range: -6.8805
Max Act: 6.5993. Min Act: -0.1700
Data Index: 6967186 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8805. Min Range: -6.8805
Max Act: 6.5680. Min Act: -0.1700
Data Index: 6738586 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8805. Min Range: -6.8805
Max Act: 6.5368. Min Act: -0.1700
Data Index: 186708 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8805. Min Range: -6.8805
Max Act: 6.5368. Min Act: -0.1700
Data Index: 2874279 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8805. Min Range: -6.8805
Max Act: 6.5368. Min Act: -0.1700
Data Index: 3257635 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8805. Min Range: -6.8805
Max Act: 6.5368. Min Act: -0.1700
Data Index: 7007469 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8805. Min Range: -6.8805
Max Act: 6.5368. Min Act: -0.1700
Data Index: 2575579 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8805. Min Range: -6.8805
Max Act: 6.4743. Min Act: -0.1700
Data Index: 242651 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8805. Min Range: -6.8805
Max Act: 6.5055. Min Act: -0.1700
Data Index: 2609354 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8805. Min Range: -6.8805
Max Act: 6.5368. Min Act: -0.1700
Data Index: 4002052 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8805. Min Range: -6.8805
Max Act: 6.5055. Min Act: -0.1700
Data Index: 4878197 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8805. Min Range: -6.8805
Max Act: 6.4743. Min Act: -0.1700
Data Index: 5574788 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8805. Min Range: -6.8805
Max Act: 6.4743. Min Act: -0.1700
Data Index: 177444 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8805. Min Range: -6.8805
Max Act: 6.4430. Min Act: -0.1700
Data Index: 5865548 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8805. Min Range: -6.8805
Max Act: 6.4743. Min Act: -0.1700
Data Index: 3657764 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19