Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 303 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0476. Min Range: -6.0476
Max Act: 6.0476. Min Act: -0.1700
Data Index: 5678453 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0476. Min Range: -6.0476
Max Act: 5.7351. Min Act: -0.1700
Data Index: 7980595 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0476. Min Range: -6.0476
Max Act: 5.7351. Min Act: -0.1700
Data Index: 7777370 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0476. Min Range: -6.0476
Max Act: 5.7351. Min Act: -0.1700
Data Index: 6528530 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0476. Min Range: -6.0476
Max Act: 5.7351. Min Act: -0.1700
Data Index: 6937455 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0476. Min Range: -6.0476
Max Act: 5.6726. Min Act: -0.1700
Data Index: 1375954 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0476. Min Range: -6.0476
Max Act: 5.7038. Min Act: -0.1700
Data Index: 1995843 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0476. Min Range: -6.0476
Max Act: 5.7038. Min Act: -0.1700
Data Index: 6353786 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0476. Min Range: -6.0476
Max Act: 5.6726. Min Act: -0.1700
Data Index: 2162562 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0476. Min Range: -6.0476
Max Act: 5.6413. Min Act: -0.1700
Data Index: 2719081 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0476. Min Range: -6.0476
Max Act: 5.6413. Min Act: -0.1700
Data Index: 1380744 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0476. Min Range: -6.0476
Max Act: 5.6413. Min Act: -0.1700
Data Index: 1380741 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0476. Min Range: -6.0476
Max Act: 5.6101. Min Act: -0.1700
Data Index: 6722514 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0476. Min Range: -6.0476
Max Act: 5.6101. Min Act: -0.1700
Data Index: 3542755 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0476. Min Range: -6.0476
Max Act: 5.6101. Min Act: -0.1700
Data Index: 5680449 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0476. Min Range: -6.0476
Max Act: 5.6101. Min Act: -0.1700
Data Index: 3455624 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0476. Min Range: -6.0476
Max Act: 5.6101. Min Act: -0.1700
Data Index: 3458123 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0476. Min Range: -6.0476
Max Act: 5.5788. Min Act: -0.1700
Data Index: 6689141 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0476. Min Range: -6.0476
Max Act: 5.5788. Min Act: -0.1700
Data Index: 1821027 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0476. Min Range: -6.0476
Max Act: 5.5788. Min Act: -0.1700
Data Index: 494974 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #19