Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3927 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4923. Min Range: -6.4923
Max Act: 6.4923. Min Act: -0.1700
Data Index: 8435586 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4923. Min Range: -6.4923
Max Act: 6.1798. Min Act: -0.1700
Data Index: 3172969 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4923. Min Range: -6.4923
Max Act: 6.1486. Min Act: -0.1700
Data Index: 3445416 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4923. Min Range: -6.4923
Max Act: 6.1173. Min Act: -0.1700
Data Index: 5877612 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4923. Min Range: -6.4923
Max Act: 6.0861. Min Act: -0.1700
Data Index: 3508919 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4923. Min Range: -6.4923
Max Act: 6.0861. Min Act: -0.1700
Data Index: 4754590 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4923. Min Range: -6.4923
Max Act: 6.0236. Min Act: -0.1700
Data Index: 8605059 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4923. Min Range: -6.4923
Max Act: 6.0236. Min Act: -0.1700
Data Index: 5588730 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4923. Min Range: -6.4923
Max Act: 5.9923. Min Act: -0.1700
Data Index: 5439606 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4923. Min Range: -6.4923
Max Act: 5.9611. Min Act: -0.1700
Data Index: 5781350 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4923. Min Range: -6.4923
Max Act: 5.9298. Min Act: -0.1700
Data Index: 6336539 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4923. Min Range: -6.4923
Max Act: 5.9298. Min Act: -0.1700
Data Index: 5485609 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4923. Min Range: -6.4923
Max Act: 5.8986. Min Act: -0.1700
Data Index: 529363 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4923. Min Range: -6.4923
Max Act: 5.8986. Min Act: -0.1700
Data Index: 4881719 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4923. Min Range: -6.4923
Max Act: 5.8986. Min Act: -0.1700
Data Index: 7421571 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4923. Min Range: -6.4923
Max Act: 5.8673. Min Act: -0.1700
Data Index: 8609248 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4923. Min Range: -6.4923
Max Act: 5.8673. Min Act: -0.1700
Data Index: 4208554 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4923. Min Range: -6.4923
Max Act: 5.8673. Min Act: -0.1700
Data Index: 4150008 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4923. Min Range: -6.4923
Max Act: 5.8673. Min Act: -0.1700
Data Index: 6194039 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4923. Min Range: -6.4923
Max Act: 5.8361. Min Act: -0.1700
Data Index: 2128908 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #19