Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3880 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9254. Min Range: -2.9254
Max Act: 2.9095. Min Act: -0.1700
Data Index: 572897 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9254. Min Range: -2.9254
Max Act: 2.9095. Min Act: -0.1700
Data Index: 572904 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9254. Min Range: -2.9254
Max Act: 2.9254. Min Act: -0.1700
Data Index: 1899967 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9254. Min Range: -2.9254
Max Act: 2.8778. Min Act: -0.1700
Data Index: 5444730 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9254. Min Range: -2.9254
Max Act: 2.8619. Min Act: -0.1700
Data Index: 3568744 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9254. Min Range: -2.9254
Max Act: 2.8619. Min Act: -0.1700
Data Index: 2304681 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9254. Min Range: -2.9254
Max Act: 2.8301. Min Act: -0.1700
Data Index: 7624044 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9254. Min Range: -2.9254
Max Act: 2.8142. Min Act: -0.1700
Data Index: 6656442 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9254. Min Range: -2.9254
Max Act: 2.8142. Min Act: -0.1697
Data Index: 2275050 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9254. Min Range: -2.9254
Max Act: 2.8301. Min Act: -0.1700
Data Index: 4792159 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9254. Min Range: -2.9254
Max Act: 2.8301. Min Act: -0.1700
Data Index: 1899966 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9254. Min Range: -2.9254
Max Act: 2.7983. Min Act: -0.1700
Data Index: 418917 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9254. Min Range: -2.9254
Max Act: 2.7983. Min Act: -0.1700
Data Index: 2275049 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9254. Min Range: -2.9254
Max Act: 2.7983. Min Act: -0.1700
Data Index: 6308496 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9254. Min Range: -2.9254
Max Act: 2.7824. Min Act: -0.1700
Data Index: 96071 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9254. Min Range: -2.9254
Max Act: 2.7824. Min Act: -0.1700
Data Index: 4792136 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9254. Min Range: -2.9254
Max Act: 2.7983. Min Act: -0.1700
Data Index: 1934797 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9254. Min Range: -2.9254
Max Act: 2.7824. Min Act: -0.1700
Data Index: 1720975 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9254. Min Range: -2.9254
Max Act: 2.7983. Min Act: -0.1700
Data Index: 5617672 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9254. Min Range: -2.9254
Max Act: 2.7664. Min Act: -0.1700
Data Index: 1720953 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19