Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3633 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2227. Min Range: -5.2227
Max Act: 5.2227. Min Act: -0.1700
Data Index: 2675060 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2227. Min Range: -5.2227
Max Act: 5.0352. Min Act: -0.1700
Data Index: 1567262 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2227. Min Range: -5.2227
Max Act: 5.0352. Min Act: -0.1700
Data Index: 5833706 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2227. Min Range: -5.2227
Max Act: 5.0352. Min Act: -0.1700
Data Index: 5006765 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2227. Min Range: -5.2227
Max Act: 4.9727. Min Act: -0.1700
Data Index: 1601981 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2227. Min Range: -5.2227
Max Act: 4.8789. Min Act: -0.1700
Data Index: 623932 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2227. Min Range: -5.2227
Max Act: 4.8477. Min Act: -0.1700
Data Index: 5833705 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2227. Min Range: -5.2227
Max Act: 4.8164. Min Act: -0.1700
Data Index: 1006130 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2227. Min Range: -5.2227
Max Act: 4.8164. Min Act: -0.1700
Data Index: 7767339 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2227. Min Range: -5.2227
Max Act: 4.8477. Min Act: -0.1700
Data Index: 1661510 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2227. Min Range: -5.2227
Max Act: 4.8164. Min Act: -0.1700
Data Index: 5907060 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2227. Min Range: -5.2227
Max Act: 4.7852. Min Act: -0.1700
Data Index: 1783132 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2227. Min Range: -5.2227
Max Act: 4.7539. Min Act: -0.1700
Data Index: 214324 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2227. Min Range: -5.2227
Max Act: 4.6914. Min Act: -0.1700
Data Index: 7767341 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2227. Min Range: -5.2227
Max Act: 4.7227. Min Act: -0.1700
Data Index: 8731917 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2227. Min Range: -5.2227
Max Act: 4.7227. Min Act: -0.1700
Data Index: 1331679 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2227. Min Range: -5.2227
Max Act: 4.6914. Min Act: -0.1700
Data Index: 2125300 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2227. Min Range: -5.2227
Max Act: 4.7227. Min Act: -0.1700
Data Index: 7064934 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2227. Min Range: -5.2227
Max Act: 4.6602. Min Act: -0.1700
Data Index: 4861460 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2227. Min Range: -5.2227
Max Act: 4.6914. Min Act: -0.1700
Data Index: 5018390 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19