Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3036 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3568. Min Range: -6.3568
Max Act: 6.3568. Min Act: -0.1700
Data Index: 6912229 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3568. Min Range: -6.3568
Max Act: 6.2005. Min Act: -0.1700
Data Index: 5636050 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3568. Min Range: -6.3568
Max Act: 6.2005. Min Act: -0.1700
Data Index: 6912228 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3568. Min Range: -6.3568
Max Act: 6.1068. Min Act: -0.1700
Data Index: 800865 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3568. Min Range: -6.3568
Max Act: 6.1068. Min Act: -0.1700
Data Index: 8554661 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3568. Min Range: -6.3568
Max Act: 6.0130. Min Act: -0.1700
Data Index: 3404891 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3568. Min Range: -6.3568
Max Act: 5.9193. Min Act: -0.1700
Data Index: 6317490 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3568. Min Range: -6.3568
Max Act: 5.8880. Min Act: -0.1700
Data Index: 5700196 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3568. Min Range: -6.3568
Max Act: 5.8568. Min Act: -0.1700
Data Index: 188935 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3568. Min Range: -6.3568
Max Act: 5.8255. Min Act: -0.1700
Data Index: 2201195 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3568. Min Range: -6.3568
Max Act: 5.8255. Min Act: -0.1700
Data Index: 7426352 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3568. Min Range: -6.3568
Max Act: 5.7943. Min Act: -0.1700
Data Index: 1919726 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3568. Min Range: -6.3568
Max Act: 5.7943. Min Act: -0.1700
Data Index: 8708452 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3568. Min Range: -6.3568
Max Act: 5.7318. Min Act: -0.1700
Data Index: 356322 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3568. Min Range: -6.3568
Max Act: 5.7318. Min Act: -0.1700
Data Index: 2857387 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3568. Min Range: -6.3568
Max Act: 5.7318. Min Act: -0.1700
Data Index: 6912230 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3568. Min Range: -6.3568
Max Act: 5.6068. Min Act: -0.1700
Data Index: 31047 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3568. Min Range: -6.3568
Max Act: 5.6068. Min Act: -0.1700
Data Index: 8554660 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3568. Min Range: -6.3568
Max Act: 5.6068. Min Act: -0.1700
Data Index: 2742236 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3568. Min Range: -6.3568
Max Act: 5.5755. Min Act: -0.1700
Data Index: 5458352 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19