Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4540 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1683. Min Range: -8.1683
Max Act: 8.1683. Min Act: -0.1700
Data Index: 4830996 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1683. Min Range: -8.1683
Max Act: 7.5745. Min Act: -0.1700
Data Index: 1917321 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1683. Min Range: -8.1683
Max Act: 7.4808. Min Act: -0.1700
Data Index: 4031925 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1683. Min Range: -8.1683
Max Act: 7.3870. Min Act: -0.1700
Data Index: 982373 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1683. Min Range: -8.1683
Max Act: 7.3558. Min Act: -0.1700
Data Index: 8633586 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1683. Min Range: -8.1683
Max Act: 7.2308. Min Act: -0.1700
Data Index: 270259 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1683. Min Range: -8.1683
Max Act: 7.2308. Min Act: -0.1700
Data Index: 1232928 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1683. Min Range: -8.1683
Max Act: 7.1995. Min Act: -0.1700
Data Index: 7865969 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1683. Min Range: -8.1683
Max Act: 7.1683. Min Act: -0.1700
Data Index: 3481026 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1683. Min Range: -8.1683
Max Act: 7.1370. Min Act: -0.1700
Data Index: 5068844 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1683. Min Range: -8.1683
Max Act: 7.1058. Min Act: -0.1700
Data Index: 4567317 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1683. Min Range: -8.1683
Max Act: 7.1370. Min Act: -0.1700
Data Index: 656773 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1683. Min Range: -8.1683
Max Act: 7.0745. Min Act: -0.1700
Data Index: 7227643 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1683. Min Range: -8.1683
Max Act: 7.0745. Min Act: -0.1700
Data Index: 2670701 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1683. Min Range: -8.1683
Max Act: 7.0120. Min Act: -0.1700
Data Index: 2404689 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1683. Min Range: -8.1683
Max Act: 7.0433. Min Act: -0.1700
Data Index: 1794853 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1683. Min Range: -8.1683
Max Act: 7.0120. Min Act: -0.1700
Data Index: 6818113 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1683. Min Range: -8.1683
Max Act: 6.9808. Min Act: -0.1700
Data Index: 1461901 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1683. Min Range: -8.1683
Max Act: 6.9495. Min Act: -0.1700
Data Index: 1845778 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1683. Min Range: -8.1683
Max Act: 6.9495. Min Act: -0.1700
Data Index: 1269346 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #19