Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3006 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2354. Min Range: -7.2354
Max Act: 7.2354. Min Act: -0.1700
Data Index: 515195 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2354. Min Range: -7.2354
Max Act: 7.2354. Min Act: -0.1700
Data Index: 7455215 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2354. Min Range: -7.2354
Max Act: 7.1729. Min Act: -0.1700
Data Index: 4147039 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2354. Min Range: -7.2354
Max Act: 7.1417. Min Act: -0.1700
Data Index: 2199008 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2354. Min Range: -7.2354
Max Act: 7.1729. Min Act: -0.1700
Data Index: 2364237 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2354. Min Range: -7.2354
Max Act: 7.0792. Min Act: -0.1700
Data Index: 5248555 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2354. Min Range: -7.2354
Max Act: 7.0792. Min Act: -0.1700
Data Index: 2680009 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2354. Min Range: -7.2354
Max Act: 7.0792. Min Act: -0.1700
Data Index: 4471434 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2354. Min Range: -7.2354
Max Act: 7.0479. Min Act: -0.1700
Data Index: 3755444 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2354. Min Range: -7.2354
Max Act: 6.9542. Min Act: -0.1700
Data Index: 6479513 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2354. Min Range: -7.2354
Max Act: 6.9229. Min Act: -0.1700
Data Index: 856515 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2354. Min Range: -7.2354
Max Act: 6.8917. Min Act: -0.1700
Data Index: 4754719 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2354. Min Range: -7.2354
Max Act: 6.8917. Min Act: -0.1700
Data Index: 3613466 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2354. Min Range: -7.2354
Max Act: 6.9229. Min Act: -0.1700
Data Index: 3725919 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2354. Min Range: -7.2354
Max Act: 6.8604. Min Act: -0.1700
Data Index: 4612236 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2354. Min Range: -7.2354
Max Act: 6.8604. Min Act: -0.1700
Data Index: 6268603 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2354. Min Range: -7.2354
Max Act: 6.8292. Min Act: -0.1700
Data Index: 5992043 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2354. Min Range: -7.2354
Max Act: 6.7667. Min Act: -0.1700
Data Index: 1594026 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2354. Min Range: -7.2354
Max Act: 6.8292. Min Act: -0.1700
Data Index: 551399 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2354. Min Range: -7.2354
Max Act: 6.7979. Min Act: -0.1700
Data Index: 150579 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #19