Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5784 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9303. Min Range: -6.9303
Max Act: 6.9303. Min Act: -0.1700
Data Index: 2824770 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9303. Min Range: -6.9303
Max Act: 6.8678. Min Act: -0.1700
Data Index: 4116920 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9303. Min Range: -6.9303
Max Act: 6.8053. Min Act: -0.1700
Data Index: 1712943 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9303. Min Range: -6.9303
Max Act: 6.7740. Min Act: -0.1700
Data Index: 7773918 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9303. Min Range: -6.9303
Max Act: 6.6490. Min Act: -0.1700
Data Index: 6026060 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9303. Min Range: -6.9303
Max Act: 6.6490. Min Act: -0.1700
Data Index: 54965 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9303. Min Range: -6.9303
Max Act: 6.5865. Min Act: -0.1700
Data Index: 6806065 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9303. Min Range: -6.9303
Max Act: 6.5865. Min Act: -0.1700
Data Index: 5756932 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9303. Min Range: -6.9303
Max Act: 6.5553. Min Act: -0.1700
Data Index: 3246585 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9303. Min Range: -6.9303
Max Act: 6.5240. Min Act: -0.1700
Data Index: 626783 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9303. Min Range: -6.9303
Max Act: 6.5553. Min Act: -0.1700
Data Index: 622082 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9303. Min Range: -6.9303
Max Act: 6.5553. Min Act: -0.1700
Data Index: 2044909 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9303. Min Range: -6.9303
Max Act: 6.5240. Min Act: -0.1700
Data Index: 93100 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9303. Min Range: -6.9303
Max Act: 6.5240. Min Act: -0.1700
Data Index: 5510662 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9303. Min Range: -6.9303
Max Act: 6.4928. Min Act: -0.1700
Data Index: 1737619 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9303. Min Range: -6.9303
Max Act: 6.4615. Min Act: -0.1700
Data Index: 2820406 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9303. Min Range: -6.9303
Max Act: 6.4615. Min Act: -0.1700
Data Index: 2452900 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9303. Min Range: -6.9303
Max Act: 6.4615. Min Act: -0.1700
Data Index: 6657697 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9303. Min Range: -6.9303
Max Act: 6.4615. Min Act: -0.1700
Data Index: 2898097 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9303. Min Range: -6.9303
Max Act: 6.4615. Min Act: -0.1700
Data Index: 3740270 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #19