Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3853 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2329. Min Range: -6.2329
Max Act: 6.2329. Min Act: -0.1700
Data Index: 5506111 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2329. Min Range: -6.2329
Max Act: 6.2017. Min Act: -0.1700
Data Index: 7575163 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2329. Min Range: -6.2329
Max Act: 6.0767. Min Act: -0.1700
Data Index: 7839014 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2329. Min Range: -6.2329
Max Act: 6.0142. Min Act: -0.1700
Data Index: 4304786 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2329. Min Range: -6.2329
Max Act: 6.0142. Min Act: -0.1700
Data Index: 2660340 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2329. Min Range: -6.2329
Max Act: 5.9517. Min Act: -0.1700
Data Index: 6109457 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2329. Min Range: -6.2329
Max Act: 5.9517. Min Act: -0.1700
Data Index: 7619847 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2329. Min Range: -6.2329
Max Act: 5.8892. Min Act: -0.1700
Data Index: 4161041 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2329. Min Range: -6.2329
Max Act: 5.8892. Min Act: -0.1700
Data Index: 4303604 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2329. Min Range: -6.2329
Max Act: 5.8892. Min Act: -0.1700
Data Index: 2852936 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2329. Min Range: -6.2329
Max Act: 5.8892. Min Act: -0.1700
Data Index: 6899361 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2329. Min Range: -6.2329
Max Act: 5.8579. Min Act: -0.1700
Data Index: 8498680 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2329. Min Range: -6.2329
Max Act: 5.8579. Min Act: -0.1700
Data Index: 2370799 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2329. Min Range: -6.2329
Max Act: 5.8579. Min Act: -0.1700
Data Index: 3297457 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2329. Min Range: -6.2329
Max Act: 5.8267. Min Act: -0.1700
Data Index: 984034 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2329. Min Range: -6.2329
Max Act: 5.8579. Min Act: -0.1700
Data Index: 7010558 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2329. Min Range: -6.2329
Max Act: 5.8267. Min Act: -0.1700
Data Index: 1737565 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2329. Min Range: -6.2329
Max Act: 5.7954. Min Act: -0.1700
Data Index: 1555367 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2329. Min Range: -6.2329
Max Act: 5.7954. Min Act: -0.1700
Data Index: 7530526 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2329. Min Range: -6.2329
Max Act: 5.7642. Min Act: -0.1700
Data Index: 7336527 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #19