Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3569 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1173. Min Range: -10.1173
Max Act: 10.1173. Min Act: -0.1700
Data Index: 5819823 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1173. Min Range: -10.1173
Max Act: 9.9923. Min Act: -0.1700
Data Index: 7470939 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1173. Min Range: -10.1173
Max Act: 10.0548. Min Act: -0.1700
Data Index: 626768 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1173. Min Range: -10.1173
Max Act: 9.9923. Min Act: -0.1700
Data Index: 6652779 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1173. Min Range: -10.1173
Max Act: 9.8673. Min Act: -0.1700
Data Index: 7725256 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1173. Min Range: -10.1173
Max Act: 9.8048. Min Act: -0.1700
Data Index: 2505846 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1173. Min Range: -10.1173
Max Act: 9.6798. Min Act: -0.1700
Data Index: 5133887 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1173. Min Range: -10.1173
Max Act: 9.7423. Min Act: -0.1700
Data Index: 8063489 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1173. Min Range: -10.1173
Max Act: 9.7423. Min Act: -0.1700
Data Index: 2401559 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1173. Min Range: -10.1173
Max Act: 9.6798. Min Act: -0.1700
Data Index: 6099088 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1173. Min Range: -10.1173
Max Act: 9.7423. Min Act: -0.1700
Data Index: 2401564 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1173. Min Range: -10.1173
Max Act: 9.6798. Min Act: -0.1700
Data Index: 69530 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1173. Min Range: -10.1173
Max Act: 9.6173. Min Act: -0.1700
Data Index: 4359543 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1173. Min Range: -10.1173
Max Act: 9.6173. Min Act: -0.1700
Data Index: 3235676 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1173. Min Range: -10.1173
Max Act: 9.5548. Min Act: -0.1700
Data Index: 4871747 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1173. Min Range: -10.1173
Max Act: 9.5548. Min Act: -0.1700
Data Index: 2774652 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1173. Min Range: -10.1173
Max Act: 9.4923. Min Act: -0.1700
Data Index: 708554 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1173. Min Range: -10.1173
Max Act: 9.4923. Min Act: -0.1700
Data Index: 5177597 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1173. Min Range: -10.1173
Max Act: 9.4923. Min Act: -0.1700
Data Index: 5100013 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1173. Min Range: -10.1173
Max Act: 9.4923. Min Act: -0.1700
Data Index: 6256309 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #19