Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 307 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9921. Min Range: -6.9921
Max Act: 6.9921. Min Act: -0.1700
Data Index: 1622993 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9921. Min Range: -6.9921
Max Act: 6.9609. Min Act: -0.1700
Data Index: 4045857 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9921. Min Range: -6.9921
Max Act: 6.9609. Min Act: -0.1700
Data Index: 326739 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9921. Min Range: -6.9921
Max Act: 6.7109. Min Act: -0.1700
Data Index: 2494438 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9921. Min Range: -6.9921
Max Act: 6.7421. Min Act: -0.1700
Data Index: 2594681 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9921. Min Range: -6.9921
Max Act: 6.6796. Min Act: -0.1700
Data Index: 6422846 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9921. Min Range: -6.9921
Max Act: 6.6484. Min Act: -0.1700
Data Index: 5282012 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9921. Min Range: -6.9921
Max Act: 6.6796. Min Act: -0.1700
Data Index: 3183978 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9921. Min Range: -6.9921
Max Act: 6.6484. Min Act: -0.1700
Data Index: 150879 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9921. Min Range: -6.9921
Max Act: 6.6171. Min Act: -0.1700
Data Index: 3124180 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9921. Min Range: -6.9921
Max Act: 6.5546. Min Act: -0.1700
Data Index: 2184539 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9921. Min Range: -6.9921
Max Act: 6.5859. Min Act: -0.1700
Data Index: 6424482 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9921. Min Range: -6.9921
Max Act: 6.5546. Min Act: -0.1700
Data Index: 5367995 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9921. Min Range: -6.9921
Max Act: 6.5546. Min Act: -0.1700
Data Index: 4010430 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9921. Min Range: -6.9921
Max Act: 6.5234. Min Act: -0.1700
Data Index: 3460767 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9921. Min Range: -6.9921
Max Act: 6.4921. Min Act: -0.1700
Data Index: 8094870 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9921. Min Range: -6.9921
Max Act: 6.4921. Min Act: -0.1700
Data Index: 189424 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9921. Min Range: -6.9921
Max Act: 6.4921. Min Act: -0.1700
Data Index: 4572732 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9921. Min Range: -6.9921
Max Act: 6.4921. Min Act: -0.1700
Data Index: 4323228 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9921. Min Range: -6.9921
Max Act: 6.4609. Min Act: -0.1700
Data Index: 8751849 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #19