Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4291 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5203. Min Range: -6.5203
Max Act: 6.5203. Min Act: -0.1700
Data Index: 1433108 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5203. Min Range: -6.5203
Max Act: 6.3641. Min Act: -0.1700
Data Index: 88667 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5203. Min Range: -6.5203
Max Act: 6.2391. Min Act: -0.1700
Data Index: 3817236 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5203. Min Range: -6.5203
Max Act: 6.2391. Min Act: -0.1700
Data Index: 824250 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5203. Min Range: -6.5203
Max Act: 6.2078. Min Act: -0.1700
Data Index: 2920517 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5203. Min Range: -6.5203
Max Act: 6.1453. Min Act: -0.1700
Data Index: 7397101 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5203. Min Range: -6.5203
Max Act: 6.1141. Min Act: -0.1700
Data Index: 5394130 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5203. Min Range: -6.5203
Max Act: 6.0516. Min Act: -0.1700
Data Index: 7902162 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5203. Min Range: -6.5203
Max Act: 6.0516. Min Act: -0.1700
Data Index: 2163591 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5203. Min Range: -6.5203
Max Act: 6.0516. Min Act: -0.1700
Data Index: 7478449 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5203. Min Range: -6.5203
Max Act: 6.0828. Min Act: -0.1700
Data Index: 2680872 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5203. Min Range: -6.5203
Max Act: 6.0516. Min Act: -0.1700
Data Index: 2484760 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5203. Min Range: -6.5203
Max Act: 6.0203. Min Act: -0.1700
Data Index: 1123539 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5203. Min Range: -6.5203
Max Act: 6.0203. Min Act: -0.1700
Data Index: 6430426 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5203. Min Range: -6.5203
Max Act: 5.9891. Min Act: -0.1700
Data Index: 2073046 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5203. Min Range: -6.5203
Max Act: 5.9891. Min Act: -0.1700
Data Index: 6636461 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5203. Min Range: -6.5203
Max Act: 5.9891. Min Act: -0.1700
Data Index: 729073 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5203. Min Range: -6.5203
Max Act: 5.9578. Min Act: -0.1700
Data Index: 7544453 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5203. Min Range: -6.5203
Max Act: 5.9578. Min Act: -0.1700
Data Index: 3218674 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5203. Min Range: -6.5203
Max Act: 5.9578. Min Act: -0.1700
Data Index: 825651 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #19